DT4CCU – A Digital Twins framework for Critical Care Unit

DT4CCU – A Digital Twins framework for Critical Care Unit | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article DT4CCU – A Digital Twins framework for Critical Care Unit Gayan Dihantha Kuruppu Kuruppu Appuhamilage, Maqbool Hussain, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5010353/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Jun, 2025 Read the published version in npj Digital Medicine → Version 1 posted 12 You are reading this latest preprint version Abstract Digital twins, long utilized in industries for enhancing efficiency, maintenance, real-time monitoring, and sustainability, are now gaining traction in healthcare, particularly with a disease-focused approach. This paper presents our journey towards the realization of a Digital Twin framework specifically designed for Critical Care, emphasizing patient safety, operational efficiency, and sustainability. Our Digital Twin architecture is uniquely structured with a dual-layer approach: a physical twin monitors real-time activities, while a conceptual twin represents ideal workflows. In Phase 1 of our research work, we aim to establish a methodology for live activity tracking. Our findings indicate that by reviewing documentation alone, we could successfully track 72% of tasks performed by nursing staff and physicians in real time. These results underscore the potential of Digital Twins to transform critical care delivery by bridging the gap between actual and ideal clinical practices. Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Introduction The primary objective of the proposed framework is to explore how the foundation for precision medicine can be effectively established and integrated into clinical practice. To achieve this, it is essential to gain a clear understanding of the interactions between healthcare providers and patients, the complexities of disease models, and the design of the healthcare system itself. By examining these factors, we aim to identify the critical elements that must be addressed and optimized to successfully implement precision medicine in routine clinical settings. To achieve this aim, we concluded that the most effective approach to collecting and interpreting data on these interactions would be through the design of a digital twin, as it can handle the design of object, evolution of the data related to the object, and changes in the model based on the evolving data 1 . Legacy work (predicting Type 2 Diabetes Mellitus by modelling generalized metabolic fluxes 2 and diabetes management 3 , Alzheimer’s disease 4 , cardiovascular diseases 5 , colorectal cancer 6 , preventing complications in pregnancy 7 , human atrial fibrillation 8 , viral infection 9 , alcohol consumption 10 , multiple Sclerosis 11 , simulating cells, organs 12 , genes and drug discovery 13 , migraine care 14 , and enabling precision cardiology15) on digital twins for health (DT4H) 16 primarily focuses directly on patients, specifically targeting the diagnosis and treatment of specific diseases or medical conditions rather than how the activities were performed. The use of digital twin in health domain is primarily because the problem lies with the fact that a lot of the information that’s collected, structured and then acted upon requires human expertise which directly leads to a significant gap between how activity is imagined and how it’s performed 17 ; which is to say that we need to know what is happening as opposed to what should happen. This will need a system which can track activity in real time and develop some insight for the user into how the information is to be presented and acted upon. Therefore, digital twin is the most practical solution to bridge the gap between work as imagined and work as done. Looking at how work is done, we know that Cognitive tasks contribute significantly to medical errors 18 , an essential component of a preventative strategy would be to intervene before judgements are made. A management strategy no matter how good, if based on flawed assumptions is likely to be flawed. So, when it comes to actions, they can be classified as structured (i.e. rolling a patient in a bed or taking blood pressure- the task has a step-by-step process, demand and frequency are well defined. The other type of actions is unstructured, these are tasks like taking a history and planning. Here the sequence of questions, the focus of examination and investigations ordered can differ from patient to patient even if they have the same presenting complaint. Since healthcare system are reliant on human beings, we needed to see how humans behave in any given work environment, how they perform activities and what might lead to error. So, introduction of human factors into both system and process design as well as an incident analysis became an essential part of the proposed framework. Patient Safety is the lens-through which all these interactions are analysed and so it became a core objective of how we design our digital twin became A tantamount objective in design and implementation of this framework as well as the most practical approach to introducing a digital twin into a healthcare environment. The other thing unique to healthcare care from a digital twin perspective is that it’s a system in flux, The demands on the services and structures are constantly changing, as new components are added, and old ones discarded the twin would need to have the ability to reflect these and incorporate these changes without significant labour to reflect the change. This would mean that the people involved with service design need familiarity with how the service structures are displayed and associations made. Part of the prediction is not only how health care outcomes would change, but what would any change mean in terms of cost and benefit. The other problem with change is understanding associations. Emergence in complicated systems would be of particular importance in healthcare twin. The state of patient safety report 2022 19 stated that the cost of medication error alone is around 98 million pounds, yet when you look at the cost in terms of clinical negligence claims its 7.9 billion pounds for the year 2020/21. In the USA the cost of medical error is around 20 billion Dollars Annually 20 . In any such system, anything which might be able to help with prediction of errors and more importantly help prevent errors before they occur would be of huge benefit for both workers and service users (patients). We can also see that our Digital twin-based framework approach will align ideally with the objectives of the global patient safety initiative 21 . Once we had decided on the focus of our project, the next issue was agreed on how meaning would be given to the collected data. This meant looking at the needs of the roles that would engage with the data to make sure the data collected is structured. It is anticipated that as time progresses, the modalities would change, the weightage of collected data would change or give new insights, as we see population drifts and as we see alteration in health seeking behaviour, we would see the implications of these in interpretation and planning of interventions. Figure 1 below shows a graphical chart of the classification of healthcare data for digital twins. With a clear way forward, we needed to see which specialty would be best to trial and validate our concepts in. We needed a cohort not limited by a specific disease type, was accustomed to collecting large amounts of data, had well prescribed management pathways independent of specific pathology and well-structured systems and process thinking embedded into his existing management pathways. The critical care unit thus appeared an ideal location to start applying the proposed framework. We started by looking at the Guidelines for Provision of Critical Care Services (GPICS) 22 . We identified that there would be anywhere between 10 to 30 people with distinct roles who might be in contact with a patient on any given day, depending on the stage of their journey though the admission process. We gathered and reviewed all the existing documentation for each of these roles and then developed process maps around specific roles, as well as around the patient themselves. The framework is structured into the following phases. Phase 1(Real-Time Activity Tracking): Can the proposed framework tract activity live? Phase 2 (Workflow Integration and Benchmarking): Can it embed data collection strategy into existing workflows? (with clinical and governance workflows as an example) and can we compare that against a standard? Phase 3 (Behavioural and Decision Support) : Can behaviour modification and decision support tools be introduced into practice? (with a focus on Bias & Noise around decision making) Phase 4 (CCU Insights and Scenario Simulation): Can the twin be used to implement an overall management strategy on a unit, by giving insights into system strengths and vulnerabilities and be used to scenario-based simulations? Phase 5 (Scaling and Interdepartmental Integration): Can the proposed framework scale for joining up of different departments of a hospital/ Health system with their own digital twins. Feasibility study for Phase 1 and groundwork for phase 2 has been completed, we have looked at incident analysis as it exists currently and how it would look with implementation and incorporation of just culture 23 and SEIPS 3.0 24 model and HFACS 25 classification into both the data collection strategy for incidence reporting & analysis. This we hope will help inform both the contributing factors as well as inform a mitigation strategy to prevent future incidents. The objectives laid for the phases have been realized with the proposed framework, Digital Twins Framework for Critical Care Unit (DT4CCU). The framework is designed using a layered approach, as it allows decoupling which ultimately helped to replicate the physical elements of the critical care unit in a Physical Digital Twin (PDT). Based on the PDT, the micro-ergonomic characteristics were then mapped to Conceptual Digital Twin (CDT). This novel approach helped to minimize the dependency between the physical elements with the actual workflow. Subsequently, this approach helped realization with increasing the reusability, testability, and refactorability of the framework. The primary motivation for leveraging this technology is to create a virtual replica of the critical care unit, enabling the organization of physical twins within complex structures through a digital overlay. The framework currently utilized Microsoft Azure because of its compatibility with Windows based NHS systems. The usage of other platforms such as Amazon Web Services (AWS), Google Cloud Platform (GCP) 26 and open-source frameworks such as Eclipse Hono + Ditto 27 and others will be investigated and adapted in future to validate the framework’s portability. Azure also supports event-driven programming methodologies, facilitating applications like historical data recording and service triggers while providing a secure and reliable service. This enabled the development of service triggers based on changes to the physical twins and historical data allowing for real-time prediction of workflows such as potential malfunctions within the treatment process or work duplication. Subsequently these technologies were facilitated with capability to develop programs to notify the relevant personnel through bi-directional communication between the physical and digital twins. The PDTs and CDTs helped to lay the foundation for implementing a digital twin system to bridge the gap between work as perceived and work as done, to determine where clinicians are, where they want to be, and how they can get there when making a diagnosis and treating diseases, thereby reducing the risks of patient deaths and supporting staff during the diagnosis and treatment process. Results Domain Perspective The information that was taken out from the Critical Care Unit (CCU) at Northampton General Hospital NHS Trust, Cliftonville, Northampton NN1 5BD. The setup consisted of 14 staff members with 10 patients over 7 days. During the study, the framework was evaluated by using takt-time analysis with the data collected from doctors(n = 11) and nurses(n = 3). The average, minimum, maximum, and count functions applied for each process group are shown for doctors in Table 1 (daily entries tasks) and for nurses in Table 2 (peri-operative tasks), Table 3 (procedure lines tasks), and Table 4 (admission tasks). Due to a lack of data reported during the data collection period task group 2 (medical diseases) and task group 5 (death and dying) were not summarized as tables, as given below. Table 5 in the methods section shows all the tasks categorized by process groups for reference. Table 1 Time (minutes) spent by doctors to perform daily entries tasks. Function F-18 (Clinical Notes) F-31 (Critical Care Unit Prescription and Administration Record) F-34 (Critical Care Patient and Family Communication Record) F-42 (Treatment Escalation Plan (TEP) To be completed for all patients) F-58 (Critical Care Unit Daily Review) F-91 (Invasive Procedure Safety Checklist: CVC/Dialysis Catheter/PICC Insertion) F-109 (Procedure Intubation) Time taken to perform daily entries tasks Average 16.66 3 15 5 19.66 17 12.5 88.76 Min 5 3 15 5 10 17 10 65 Max 30 3 15 5 30 17 15 115 Count 3 1 1 2 5 1 2 Table 2 Time (minutes) spent by nurses to perform peri-operative tasks. Function F-37 (Trust Core Neurovascular Limb Assessment (Adult)) F-66 (Summary of Wound Care) Time taken to perform peri-operative tasks Average 2.50 1 3.50 Min 2 1 3 Max 3 1 4 Count 2 1 Table 3 Time (minutes) spent by nurses to perform procedure lines tasks. Function F-6 (Trust Peripheral Venous Cannula (PVC) Care Plan (Adult)) F-9 (Wound Care Plan) F-10 (Trust Core Care Plan and Risk Assessment for Patients with Nasogastric Feeding Tube (Adult)) F-12 (Trust Core Care Plan Care of the Patient with an Indwelling Urinary Catheter (Adult)) F-32 (Trust Critical Care Arterial Cannula (AC) Care Plan) Time taken to perform procedure lines tasks Average 2 2 2 1.40 2 9.40 Min 1 2 2 1 1 7 Max 4 2 2 2 3 13 Count 6 2 3 6 6 Table 4 Time (minutes) spent by nurses to perform admission tasks. Function F-5 (Trust Bedrail Assessment and Core Care Plan (Adult)) F-35 (Food Record Chart Nutrition and Diabetic Services) F-63 (Critical Care Nursing Assessments and Care Plans) F-77 (Critical Care Patient Property Form) F-113 (Trust Core Patient Activities of Daily Living - Initial Assessment) Time taken to perform admission tasks Average 1 2 23.33 3 4 33.33 Min 1 2 20.00 3 4 30 Max 1 2 25.00 3 4 35 Count 4 1 3.00 1 1 Table 5 Routing (integers) and Event Grid latency (milliseconds) of the Azure IoT Hub. Timestamp Telemetry messages sent (Sum) Event Grid deliveries (Sum) Routing: message latency for messages/events (Avg) Event Grid latency (Avg) 20/06/2024 12:00 66 66 149.12 179.39 20/06/2024 18:00 7 7 208.42 237.42 21/06/2024 00:00 4 4 188 188.25 21/06/2024 06:00 23 23 155.78 190.39 21/06/2024 12:00 4 4 166.50 213.25 21/06/2024 18:00 43 43 164.37 206.41 22/06/2024 00:00 74 74 150.09 185.14 22/06/2024 06:00 23 23 166.26 173.56 22/06/2024 12:00 27 27 181.14 197.33 22/06/2024 18:00 27 27 147.03 175.29 23/06/2024 00:00 79 79 148.46 159.37 23/06/2024 06:00 5 5 208.8 202.60 24/06/2024 12:00 3 3 203 198 25/06/2024 12:00 5 5 234 183.80 26/06/2024 18:00 6 6 186.66 173.83 27/06/2024 06:00 3 3 181.66 234 27/06/2024 18:00 4 4 162 181.50 Table 1 . Time (minutes) spent by doctors to perform daily entries tasks. Table 2 . Time (minutes) spent by nurses to perform peri-operative tasks. Table 3 . Time (minutes) spent by nurses to perform procedure lines tasks. Table 4 . Time (minutes) spent by nurses to perform admission tasks. First, the daily entries process group by doctors included n = 11 shifts. Out of 22 tasks, only 7 tasks were reported during the data collection period. The F-58 (Critical Care Unit Daily Review) and F-18 (Clinical Notes) were frequently used in each shift. As previously identified by the domain experts, Critical Care Daily Review took on average 6 minutes to perform. The F-109 (Procedure Intubation) task had the lowest variability with an average of 12.5 minutes. Additionally, doctors took an average of 88.76 minutes to perform tasks in the daily entries process group. Second, the peri-operative process group by nurses was recorded only during 2 shifts, which included 6 tasks, but only 2 were reported. Tasks included in the process group but not recorded were F-24 (Peri-operative Care Pathway), F-25 (Trust Core Care Plan Colostomy/Ileostomy), F-38 (Assessment to be carried out before elective surgery and/or endoscopy to identify patients with or at increased risk of OCJ or vCJD), and F-105 (Maintenance Check List Faecal Collection System). Nurses took an average of 3.5 minutes to perform peri-operative tasks, with a variability of 0.5 minutes. Third, the procedure lines process group recorded data from 5 shifts, and out of 13 tasks, only 5 were reported during the data collection period. The following tasks were included in the process group but not recorded: F-16 (Adult Acute Pain Service Patient Controlled Analgesia), F-46 (Trust Core Care Plan: Tracheostomy (Adult)), F-53 (Adult Transfusion Prescription and Administration Record), F-54 (Diabetic Ketoacidosis (DKA) Management for Adults), F-56 (Intravenous Heparin Chart), F-72 (Critical Care Therapies Treatment Record), F-84 (Critical Care Continuous Renal Replacement Therapy Prescription Form & Chart for Citrate), and F-97 (MRI Patient Screening Questionnaire and Consent Form). The F-6 (Trust Peripheral Venous Cannula (PVC) Care Plan (Adult)), F-12 (Trust Core Care Plan Care of the Patient with an Indwelling Urinary Catheter (Adult)), and F-32 (Trust Critical Care Arterial Cannula (AC) Care Plan) tasks were recorded in every process group, with averages of 2, 1.4, and 2 minutes each. Overall, nurses took an average of 9.4 minutes to perform procedure lines tasks, with a minimum of 7 minutes and a maximum of 13 minutes. Finally, the admission process group recorded data from 4 shifts, with data recorded for 6 out of 9 tasks. The tasks F-14 (Trust Pain Assessment Tool and Core Care Plan for Patients with Learning Disabilities (Adults) and Patients who have Dementia or Cognitive Impairment), F-24 (Peri-operative Care Pathway), and F-101 (Parenteral Nutrition: Initial Review Form) did not record any data during the data collection period. On average, it took 34.33 minutes to complete an admission process group. From the domain perspective, data collection was integrated as an additional task within the existing workflow. This led to staff members spending less time on tasks such as the F-5 (Trust Bedrail Assessment and Core Care Plan (Adult)) during the admission process, even though these tasks typically require more time due to the busy nature of shift hours. In practice, these tasks often took more than one minute to complete. It was observed that staff members would log the start and end times for these tasks at their initiation, rather than upon completion, which did not reflect the actual time taken. On average, doctors took 88 minutes to complete their daily entries, with significant variation ranging from 65 to 115 minutes. In contrast, nurses spent 3 to 4 minutes on perioperative tasks, 7 to 13 minutes on procedure lines, and 30 to 35 minutes on admission tasks, showing less variation. This difference is attributed to doctors primarily performing unstructured tasks, whereas nurses engage in more structured tasks. Technology Perspective Table 5 below shows the routing and event grid latencies of the IoT Hub from the data collection period from 2024/06/20 to 2024/06/27. During this period, the highest recorded telemetry events were 79 on 2024/06/23, and the lowest were 3 on 2024/06/24 and 2024/06/27. The routing latency fluctuated, ranging from 149 milliseconds to 208 milliseconds, and the event grid latency ranged from 179 milliseconds to 237 milliseconds. The number of telemetry events corresponds to the latencies, but factors such as the size of the telemetry payload and the time between two telemetry events were also could cause to higher latencies. Due to a lack of data recorded during the data collection period, some rows were removed from the table. Table 5 . Routing (integers) and Event Grid latency (milliseconds) of the Azure IoT Hub. Table 6 below shows the latency data for two Digital Twins instances during the period from 2024/06/20 to 2024/06/27, recording average latency data in milliseconds for API requests and routing operations. The physical Digital Twins instance recorded the highest latency at 208.5 milliseconds on 2024/06/26 and the lowest at 12.508 milliseconds on 2024/06/20. The routing latencies were variable, with the highest recorded latency being 399.403 milliseconds on 2024/06/23 and the lowest latency being 32.226 milliseconds on 2024/06/20. The conceptual Digital Twins instance recorded an average API request latency of 338.213 milliseconds on 2024/06/23 and the lowest at 23.861 milliseconds. The routing latency for the conceptual instance varied, with the highest recorded at 221.364 milliseconds on 2024/06/27 and the lowest at 102.357 milliseconds on 2024/06/23. Both Digital Twins instances showed variability in latency, with both instances recording higher average latencies on 2024/06/23, possibly suggesting external factors such as load during the data collection period. As per the Table 5 rows were elminated from the table due to lack of data collected during the period. Table 6 API Request (milliseconds) and Routing latency (milliseconds) of physical and conceptual digital twins instances. Timestamp nhs-rns-rns01-78h-conceptual-twins-adt nhs-rns-rns01-78h-physical-twins-adt API Requests Latency (Avg) Routing Latency (Avg) API Requests Latency (Avg) Routing Latency (Avg) 20/06/2024 12:00 113.61 112.03 12.50 319.57 20/06/2024 18:00 31.25 115.52 36.07 348.56 21/06/2024 00:00 32.11 121.59 13.66 32.32 21/06/2024 06:00 29.00 109.88 15.24 16.06 21/06/2024 12:00 23.86 110.42 64.59 15.40 21/06/2024 18:00 23.66 113.06 29.52 228.14 22/06/2024 00:00 36.14 117.45 141.49 201.99 22/06/2024 06:00 30.04 116.87 29.04 189.96 22/06/2024 12:00 239.33 118.07 35.24 148.26 22/06/2024 18:00 301.09 113.45 26.04 365.75 23/06/2024 00:00 223.71 106.08 23.55 399.40 23/06/2024 06:00 338.21 102.35 23.19 37.49 26/06/2024 18:00 39.29 151.79 208.50 125.79 27/06/2024 18:00 35.08 221.36 184 159.55 Table 6 . API Request (milliseconds) and Routing latency (milliseconds) of physical and conceptual digital twins instances. Table 7 below shows the number of event triggers from 2024/06/20 to 2024/06/27. The highest number of triggers occurred on 2024/06/22, and the lowest on 2024/06/27. The IoT Hub to SQL DB, IoT Hub to Physical Twins ADT, and Physical Twins ADT to Conceptual Twins ADT recorded similar values for the period, but Conceptual Twins ADT to SQL DB recorded fewer triggers. Additionally, there are inconsistencies in the Conceptual Twins data due to users using the online dashboard to record tasks without using IoT devices. The Conceptual Twins recorded SQL DB triggers only if the task or action was completed. As with Table 5 and Table 6 , some rows were eliminated due to a lack of data recorded during the data collection period. Table 7 Function trigger count. Timestamp Function Count (Sum) IoT-Hub To SQL-DB IoT-Hub To Physical-Twins-ADT Physical-Twins-ADT To Conceptual-Twins-ADT Conceptual-Twins-ADT To SQL-DB 20/06/2024 12:00 66 66 66 20 20/06/2024 18:00 7 7 7 6 21/06/2024 00:00 4 4 4 4 21/06/2024 06:00 23 23 23 22 21/06/2024 12:00 4 4 4 4 21/06/2024 18:00 43 43 43 30 22/06/2024 00:00 74 74 74 46 22/06/2024 06:00 23 23 23 8 22/06/2024 12:00 27 27 27 6 22/06/2024 18:00 27 27 27 20 23/06/2024 00:00 79 79 79 62 23/06/2024 06:00 5 5 5 2 24/06/2024 12:00 3 3 3 0 25/06/2024 12:00 5 5 5 0 26/06/2024 18:00 6 6 5 4 27/06/2024 06:00 3 3 3 0 27/06/2024 18:00 4 4 4 7 Table 7 . Function trigger count. During the initial phase of the implementation, we observed a latency of 10 seconds when querying physical twins. This issue persisted as staff members often recorded both start and end events with brief period of time, despite the fact that tasks generally took more than 10 seconds to be completed for any given scenario. This resulted in duplication of activities and tasks twins in the conceptual twins during each event. To address this latency, we implemented the API calls using Azure SDK to retrieve digital twins as a default rather relying on query. This made querying became less feasible when the digital twins required constant read and write operations. Notably, the study used dynamically generated instances of digital twins. The digital twins were created or deleted based on the physical overview of the critical care unit. The Table 8 and 9 shows the dynamic resource allocation based on the demand. For example, if a newly registered staff member started an activity a new barcode reader, a set of ports, barcode reader, session, staff, activity, and task digital twins would be generated in both physical and conceptual digital twin instances. In such cases, naming digital twins presented unique problems since the naming conventions and Azure Event Grid tend to execute each event nanoseconds apart. So, any standard time-based identification was incompatible and caused unpredictability due to duplication of digital twins. Therefore, globally unique identifiers (GUIDs) were suffixed to digital twins ids to eliminate duplication. Also, GUIDs were used to track each telemetry event from the beginning to the end of the system. A GUID were attached as an identifier to each IoT telemetry event which helped to identify and telemetry track events from the Event Grid. Table 8 Dynamic device allocation in IoT Hub Timestamp Total devices (Avg) Attestation attempts (Sum) Registration attempts (Sum) Devices assigned (Sum) 20/06/2024 12:00 16.93 23 22 22 20/06/2024 18:00 18 0 0 0 21/06/2024 00:00 18 4 4 4 21/06/2024 06:00 18.42 12 12 12 21/06/2024 12:00 19 0 0 0 26/06/2024 18:00 19 3 3 3 27/06/2024 06:00 19 2 2 2 27/06/2024 18:00 19 2 2 2 Table 9 Dynamic twins allocation in Azure Digital Twins. Timestamp nhs-rns-rns01-78h-physical-twins-adt nhs-rns-rns01-78h-conceptual-twins-adt Twin Count (Sum) Twin Count (Sum) 20/06/2024 12:00 67 48 20/06/2024 18:00 70 49 21/06/2024 00:00 72 50 21/06/2024 06:00 83 55 21/06/2024 12:00 85 56 21/06/2024 18:00 107 67 22/06/2024 00:00 144 85 22/06/2024 06:00 155 90 22/06/2024 12:00 169 97 22/06/2024 18:00 193 111 23/06/2024 00:00 233 131 23/06/2024 06:00 235 132 26/06/2024 18:00 242 135 27/06/2024 18:00 245 136 Table 8 . Dynamic device allocation in IoT Hub. Table 9 . Dynamic twins allocation in Azure Digital Twins. Moreover, during the implementation phase of this study the client raised requirements for security, stability, maintainability, and low cost of maintenance. The Microsoft .NET was used as default environment to develop all the software required by the framework as it has more stable releases and documentation. This approach reduced conflicts when projects interact with each other and increased maintainability of the code base. By using Azure SDK for .NET for client and management services helped eliminate many external dependencies which enhanced the security and stability of the code. This approach contributed to the implementation phase the project with less time and improved quality and control in mind. In addition, standard or basic features of the Azure platform led to unique challenges. Such as cold start the latency of function apps which would sleep after inactivity and in some cases took at least 90 seconds to start. This caused duplication and errors in the conceptual twins as the digital twins were either not created or did not have updated properties. Instead of implementing queues in the IoT Hub client, the subscription plans were upgraded to premium versions and event grid trigger functions were integrated into a single app project to reduce costs and increase availability. This significantly eliminated data duplication in the conceptual twins. Moreover, the barcode readers used Bluetooth to communicate with the IoT client computer. Which limited the number of patients that could be covered in the CCU. Barriers and interferences, such as the thick wall dividing the east and west wards and glass dividers restricted the signal strength of each barcode reader to maximum 5 meters. Figure 1 shows the IoT client’s location within the physical layout of the Critical Care Unit (CCU). To record data, manual forms were used as an alternative to cover more patients and to supplement the use of barcode readers. During the production phase many nurse and support staff adopted a hybrid method due to limited access to computers and barcode readers. Next, Azure uses a global naming schema for identifying its resources. For example, if a resource can establish connectivity with the outside, its name is typically permanent and cannot be changed in the future. Each name also has constraints, such as alphabetical or numerical limits and character length restrictions. Using full names to identify each resource can be complex and may require recreating the entire resource with a different name. To address this, the study employed a four-part naming strategy and used the NHS Digital Data Repository to create a standardized, uniquely readable identification system for naming these resources to overcome the limitations. First, to identify the project, the study used the “uod-nhs” as University of Derby – NHS to distinguish other ongoing projects. Secondly, to identify the hospital and unit, formatted as "rns-rns01-78h," which includes the region, hospital ID, and department ID as the prefix. Thirdly, two or three words to identify the project name. Last, initials of the Azure service name, such as "sqldb" for SQL Database, "wa" for Web App, and "egt-fa" for Event Grid Trigger Function Apps, were used. This approach streamlined the naming process, ensuring each resource name was unique among globally deployed resources, and helped scale each resource without causing conflicts. To sum up the technology perspective, we noticed that Azure Cloud maintained connectivity with IoT devices throughout the data collection period. The documentation was well-written and easy to implement. Additionally, the IoT Hub executed operations with latency below 1 second. The study's main feature, integrating multiple layers, performed well with latency of less than 500 milliseconds. Azure Entra's application scope helped establish secure, symmetric-key-based applications for each endpoint to manage resources with its built-in HTTP client. The built-in features of the Microsoft SDK helped reduce reliance on external dependencies and facilitated upgrading the source code to more recent stable releases without conflicts. The Azure Resource Manager SDK provided a programmable interface to allocate resources in Azure Cloud, enabling dynamic management of resources. Moreover, the naming strategy reduced clashes between globally deployed resources and streamlined the implementation process. Discussion From a domain perspective, no data was intentionally collected about individual patients or specific workers at first phase. The primary goal was to focus on tracking and quantifying activity while minimizing any potential influence on data collection and performance. This approach ensured that the observed behaviours were as close to natural as possible. The Standard Operating Procedures (SOPs) reviewed during this phase were found to poorly reflect the actual work being performed. A more effective methodology would have involved interviewing various staff members to gain insights into their roles and daily activities. This would have provided a more accurate picture of the work environment and processes. Process mapping for each activity proved valuable in revealing discrepancies between how care was intended to be delivered versus how it was actually delivered. For example, the analysis of nursing documentation revealed that nurses are required to complete 15 separate documents totalling over 80 pages within the first 24 hours of a patient’s admission. Despite the volume, only three did not documents contained redundant information. Analysing and eliminating these redundancies could save approximately 25 minutes per shift, translating to a cumulative reduction of five hours of nursing time per shift, per day. Similarly, more than half of the documentation performed by physiotherapists was found to duplicate nursing reviews. Additionally, the review of pharmacists' roles highlighted that a significant portion of their time was spent retrieving data already gathered by other systems, resulting in redundant tasks with limited value. Another key insight was that during periods of high demand, staff often delayed documentation until after tasks were completed. This suggests that to track activities in real time, data collection must extend beyond documentation to include metrics like changes in patient physiology, position, and interventions provided. As we moved into fault point analysis for Phase 2, it became evident that incident investigations disproportionately attributed errors to individuals, with limited attention given to systemic and process-related factors that contribute to harmful events. The lack of system and process thinking in service design was apparent, and when incidents occurred, the absence of comprehensive data and process maps made it difficult to trace back and identify the root causes. The proposed framework envisioned to incorporate a comparative analysis of activity against an ideal and highlight discrepancies, helping with better understanding of root causes around patient safety events. Digital Twins (DTs) have their origins in the manufacturing domain, where they were initially applied within Product Lifecycle Management (PLM) systems 28 . To encapsulate the essential features and components of PLM, the "Mirrored Spaces Model" was introduced, which consists of real space, virtual space, and a linking mechanism to manage data flow between them. Legacy work (aerospace 29 , energy 30 , maritime 31 ) shows capabilities and intent of DTs were well-suited not only to the manufacturing industry 32 but other domains as well. As their potential became evident, DTs gained attention from other sectors, becoming a strategic technology for key business players 33 . Although DTs are now being explored in diverse domains, including healthcare, achieving optimal benefits relies on how well the domain aligns with the core characteristics of DT models 34 . For example, in the aerospace qualification domain, there is a clear alignment between physical objects (POs) and their virtual DT counterparts, making it straightforward to model DT properties according to the characteristics of the POs. For instance, the "Reflection" property 35 can be easily implemented to mirror the behaviour of a robotic system (Cobot) in both physical and digital environments, enabling synchronization of state changes 36 . However, realizing similar capabilities in healthcare is more complex. Healthcare POs are not limited to tangible physical objects (e.g., blood pressure devices); they can also include live observations, workflows, patients, clinicians, or clinical guidelines. Moreover, a single PO may be linked to multiple other POs, each with its own representative DT model. For example, in this study, a barcode device is associated with different roles (nurses, consultants, etc.), each with its own DT model to track activities within the CCU. This creates a many-to-many relationship between healthcare POs and DTs, complicating the design and implementation of DT models in this domain. To address these complexities, a novel layered approach for DT design is proposed. The Physical Digital Twin (PDT) layer represents twins associated with tangible objects and their complementing components—for instance, a barcode scanner and its communication ports. The Conceptual Digital Twin (CDT) layer represents twins of key domain entities, such as roles (nurses, consultants), workflows, observations, and tasks (e.g., CCU forms), which are crucial to fulfilling the business requirements. This multi-layered approach offers two primary advantages: first, it reduces the complexity of domain modelling; second, it allows for a more comprehensive realization of DT capabilities, maximizing their benefits in healthcare applications. The current phase of the DT4CCU framework was implemented as an additional task within the existing workflow. This approach limited both the quantity and type of data we could collect due to the demanding environment of the CCU. Our focus in this phase was primarily on capturing the start and end times of tasks, rather than the granular details of the tasks themselves, due to the complexities of recording data while administering lifesaving treatments. It became clear that collecting data for a digital twin framework as an extra task for staff is not feasible, especially as some staff members were initially hesitant to use it. Nevertheless, the framework’s design is flexible enough to integrate various data sources, and in subsequent phases, data from EMRs and other EHRs will be incorporated. From a platform perspective, Azure Cloud reduced the time spent on implementing the DT framework due to its extensive documentation and the trustworthy environment it provides to secure interactions. The key limitation, however, is the lack of in-house capability to replicate Azure services. Open-source frameworks such as Eclipse Ditto and Hono offer alternatives for implementing DT4CCU on-premises 27 However, implementing an open-source framework in a high-risk industry such as healthcare conflicts with their liability risks. Also, open-source Alternatives such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) were considered due to their performance in Apache benchmarks 26 , but the NHS infrastructure is based on Microsoft Windows OS. To reduce architectural conflicts and enhance security, study chose Microsoft's Azure Cloud to implement this framework. The Critical Care Unit (CCU) adapts to patient demand and staff availability, causing fluctuations in the need for barcode readers. To reflect these changes, the study integrated the IoT Hub client application with an HTTP API, allowing dynamic management of IoT devices in the cloud based on demand. The endpoint used for managing IoT devices—enabling creation, reading of symmetric keys, and deletion operations in Azure IoT Hub via the Device Provisioning Service—was secured to be accessible only by the IoT Hub client application using Azure Entra scope. Additionally, requiring a symmetric key in the HTTP request headers further enhanced security, enabling real-time adjustments to the digital twins based on demand. From an interdisciplinary perspective, the way we have designed the digital twin can easily be used in other industries where human resources and complex rules are an essential part of the delivery of services. Another group that would benefit from this approach is where predictive judgment is required for complex data with limited information for people to make decisions. These two unique characteristics of our digital twin design mean that it can, on one hand, improve efficiency and be easily deployable in complex environments like government departments, such as taxation, and similarly be useful for entities like small businesses to help with the visualization and validation of their day-to-day operations. Other examples would include the insurance industry, where predictive judgment is an essential part of calculations. This is achievable because we have structured the information around known models of service design and business management, with the intention that experts do not need to face a sharp learning curve to introduce the technology. As we design interfaces as part of phase 2, our next focus will be on designing them in a manner that allows people with limited knowledge of system design and processes to easily build a twin without direct expert input. Our motivation remains healthcare, a field that changes how things are done significantly and regularly, yet we believe that such an approach would potentially allow our model to be used in most industries where even people with limited knowledge of digital twinning can apply the technology to meet their needs. Methods The proposed framework employs a four-step process model, systematically divided into five distinct phases. Each phase utilizes the four-step process, as illustrated in Fig. 2 . 1) Domain Knowledge Acquisition : Conceptual Digital Twins (CDTs) are created through a thorough inspection and process mapping of takt time analysis, critical care unit guidelines, and forms used to document the treatment process. 2) Key Resources Knowledge Acquisition : Physical Digital Twins (PDTs) are developed by analysing workflows and business processes (e.g., BPMN, schemas, and protocols) using data from EMR systems, diagnostic devices, and observation forms. 3) Integration of PDT and CDT : The PDT and CDT models are combined into a unified framework that reflects all relationships and mappings between the components. 4) Design Evaluation and Execution : The design is validated against artifacts in the target platform (Microsoft Azure in this case) to ensure robust implementation and execution environments. Throughout this process, the overall design aligns with the foundational criteria and requirements specific to the healthcare domain. For instance, domain knowledge is acquired through rigorous inspection of workflows, CCU forms, protocols, guidelines, and consultations with healthcare professionals. The design undergoes comprehensive validation through testing and baseline verification to ensure consistency. Additionally, the design incorporates criteria for compliance with healthcare standards (e.g., security and communication protocols like HL7). Finally, the knowledge generated from the DT models can be shared across other organizations. 1) Domain Knowledge Acquisition Identifying process maps is a key part of creating the Conceptual Digital Twins Layer (CDTL). During the design phase, we scanned observation forms (n = 116) to classify them according to the related processes carried out by nurses and doctors. These paper-based observation forms were empty, containing no patient-related data, and were used to identify data points and the structure of the diagnosis and treatment processes. Due to the unstructured nature of tasks performed by doctors, we created process maps (n = 1) using forms to record daily entries (n = 21). In contrast, the structured nature of tasks performed by nurses led to create process maps (n = 6) using forms to document 1) daily entries (n = 22) 2) peri-operative tasks (n = 1) 3) medical diseases (n = 1) 4) procedure lines (n = 1) 5) admissions (n = 1) 6) death and dying processes (n = 1). The study was limited in time and scope, focusing on user roles (n = 2), with process maps created for doctors (n = 1) and nurses (n = 6). Table 10 shows classification of observation forms used in diagnosis and treatment tasks by doctors and nurses based on process groups. As shown in Fig. 3 the classification was then mapped into process maps to identify the rules, roles, processes, and standards of each workflow. Breaking down each task into a flowchart helped to communicate domain knowledge about tasks and activities in the Critical Care Unit to technical experts. During this phase, the study identified forms, tasks, actions, patients, staff, and units as Conceptual Digital Twins (CDT). Table 10 Classification of observation forms used in diagnosis and treatment tasks by doctors and nurses into process groups. Role Process Map Tasks Doctor Daily Entries 1) WZW101 09/17 Clinical Notes 2) NGV903 03/19 Consent Form 1 - Patient Agreement to Investigate or Treatment 3) NGV1220 04/23 Critical Care Unit Prescription and Administration Record 4) NGV1284 10/17 Critical Care Patient and Family Communication Record 5) NGV1550A 09/23 Treatment Escalation Plan (TEP) To be completed for all patients 6) NGV1914 01/18 Critical Care Unit Daily Review 7) NGV2031 11/20 Do not Attempt Cardiopulmonary Resuscitation 8) NGV2035 04/18 Critical Care Microbiology Report 9) NGV2064 07/22 Critical Care Unit Admission 10) NGV2343 06/21 Major Haemorrhage Protocol Blood Administration Record Dial 2222 11) Medical Admission Data 12) Critical Care Microbiology Results Record 13) Invasive Procedure Safety Checklist: Tracheostomy 14) Invasive Procedure Safety Checklist: CVC/Dialysis Catheter/PICC Insertion 15) Invasive Procedure Safety Checklist: Arterial Line 16) Procedure Checklist: Pruning 17) Mental Capacity Assessment 18) Patient Demographics 19) Parental Nutrition Prescription 20) Medical Discharge Data Nurse Daily Entries 1) FNGV1626 13/18 Malnutrition Universal Screening Tool (Must) and Core Care Plan (Adult) 2) WZP198 10/17 Fluid Balance Charts (Adults) 3) WZP538 01/19 Observation Chart for NEWS (National Early Warning Score) 4) NGV785 11/22 Critical Care Unit 5) NGV836 12/21 Adult Prescription and Administration Record 6) NGV1220 04/23 Critical Care Unit Prescription and Administration Record 7) NGV1284 10/17 Critical Care Patient and Family Communication Record 8) NGV1497 12/17 Patient Orientation Checklist - Nursing Staff to Complete 9) NGV1516 10/15 This is my Hospital Passport For people with learning disabilities coming to hospital 10) NGV1580 05/18 Adult Inpatient Admission Information Essential Assessments Activities of Daily Living Initial ADL Assessment 11) NGV1742 03/17 Critical Care Pressure Ulcer Prevention Assessment and Core Care Plan (Adult) 12) NGV1835 06/19 Nurse Handover/Transfer Safety Checklist for Receiving Ward 13) NGV1881 03/16 Duty of Candour Member of Staff carrying out Duty of Candour 14) NGV1914 01/18 Critical Care Unit Daily Review 15) NGV2431 08/21 Summary of Wound Care 16) NGV2441 04/22 Critical Care Nursing Transfer Form 17) NGV2444 03/23 Critical Care Eye Care Plan 18) NGV2485 01/22 Bowel Monitoring Care Plan 19) NGV2690 10/23 Critical Care Transfer Safety Checklist for Receiving Ward 20) Critical Care Water low Risk Assessment Score 21) NGV541 01/14 Trust Falls Assessment and Core Care Plan (Adult) 22) NGV1358 10/17 Trust Initial Pressure Ulcer Assessment (Adult) Peri-Operative 1) WZQ552 03/21 Peri-operative Care Pathway 2) PC711 12/08 Trust core care plan colostomy/ileostomy 3) NGV1380 12/10 Trust Core Neurovascular Limb Assessment (Adult) 4) PC1384 01/18 Assessment to be carried out before elective surgery and/or endoscopy to identify patients with or at increased risk of OCJ or vCJD 5) NGV2431 08/21 Summary of Wound Care 6) F-105 Maintenance Check List Faecal Collection System Medical Diseases 1) NGV285 03/03 Fit Chart 2) NGV312 02/16 Adult neurological observation chart incorporating pupillary response and limb movements 3) NGV889 11/04 EU Peak Flow Chart – Inpatient 4) NGV1424 03/23 Adult Insulin Prescription and Diabetes 5) NGV1598 05/18 Diabetes sugar monitoring chart for patients not on insulin 6) Glasgow Modified Alcohol Withdrawal Scale (GMAWS) Procedure Lines 1) NGV1176 07/19 Trust Peripheral Venous Cannula (PVC) Care Plan (Adult) 2) NGV1586 03/18 Wound Care Plan 3) NGV1660 03/14 Trust Core Care Plan and Risk Assessment for Patients with Nasogastric Feeding Tube (Adult) 4) NGV1590a 07/17 Trust Core Care Plan Care of the Patient with an Indwelling Urinary Catheter (Adult) 5) NGV090 08/22 Adult Acute Pain Service Patient Controlled Analgesia 6) NGV1239 05/18 Trust Critical Care Arterial Cannula (AC) Care Plan 7) NGV1644 02/16 Trust Core Care Plan: Tracheostomy (Adult) 8) NGV1771 09/20 Adult Transfusion Prescription and Administration Record 9) NGV1798 10/20 Diabetic Ketoacidosis (DKA) Management for Adults 10) NGV1854 05/18 Intravenous Heparin Chart 11) Critical Care Therapies Treatment Record 12) Critical Care Continuous Renal Replacement Therapy Prescription Form & Chart for Citrate 13) MRI Patient Screening Questionnaire and Consent Form Admissions 1) NGV1523 07/18 Trust Bedrail Assessment and Core Care Plan (Adult) 2) NGV1545 08/18 Trust Pain Assessment Tool and Core Care Plan for Patients with Learning Disabilities (Adults) and Patients who have Dementia or Cognitive Impairment 3) WZQ552 03/21 Peri-operative Care Pathway 4) NGV1349 08/17 Food Record Chart Nutrition and Diabetic Services 5) NGV2109 07/20 Critical Care Nursing Assessments and Care Plans 6) Critical Care Patient Property Form 7) Parental Nutrition: Initial Review Form 8) Trust Core Patient Activities of Daily Living - Initial Assessment 9) Trust Bedrail Assessment and Core Care Plan (Adult) Death and dying 1) NGV093 01/21 Mortuary Card 2) NGV1274 05/20 Notification of death of a patient - checklist Retain on front of notes 3) NGV1715 06/17 Clinical Notes Achieving Individual Priorities of Care for the Dying Person and their family Doctor Review 4) NGV1717 06/19 Individualised care at the end of life - Care round record sheet (To be used in place of enhanced are round document) 5) NGV1718 03/18 Clinical Notes Individualised Care for the Dying Person and their family (Continued) 6) NGV1720 08/17 Individualised Plan of Care for the Dying Person and their Family Multidisciplinary Communication Sheet 7) NGV2245 04/20 Death Verification Report 8) Tissue Donation Referral Form – Email 9) H. M. Coroner - Referral Form 10) End of life care checklist Table 10 . Classification of observation forms used in diagnosis and treatment tasks by doctors and nurses into process groups. 2) Key Resources Knowledge Acquisition We observed non-patient medical data, diagnostic devices, and observation forms used in diagnosis and treatment processes to analyse the business and workflow of the critical care unit in order to build the Physical Digital Twins Layer (PDTL). During this phase, alternatives such as web, mobile, and desktop apps were considered to interface physical twins with digital twins, but the study employed a hybrid approach which utilized barcode readers as IoT devices, paper sheets for taking manual entries, and a web-based interface to record the start and end times of tasks by the staff. The main reason for this approach was to provide alternative means for clinicians to interface with the digital twins without changing existing workflows. This phase, the study identified the computer, barcode reader, sessions, and unit as Physical Digital Twins (PDT) within the digital twins framework. 3) Integration of PDT and CDT During this phase, we identified the session digital twins to store information about the recorded event. The Session CDT was designed to store property values such as Patient ID, Staff ID, Form ID, Start and End Timestamps, and an Is Session Valid Boolean flag. If the Is Session Valid flag is true, then the values in the property fields will be matched with existing twins in the CDTL. For example, if a new staff member initiates an action on a task for an admitted patient, the Session PDT is used to create new Staff CDT, Patient CDT, Task CDT, and Action CDT. The Task CDT and Action CDT are used to record the start and end timestamps. Every time they interact with the patient, a new Action CDT will be created under their particular Task CDT, recording their start and end timestamps. In the above example, if the staff member completes the action, they will set the Is Action Completed Boolean flag to true and update the end timestamp property fields. If the staff member completes a task, the Task CDT will have the Is Task Completed flag set to true, and the end timestamp property fields will be updated. When a staff member creates another action on the same Task CDT, a new Task CDT will be created, and ongoing actions will be displayed under the new Task CDT. 4) Design, Evaluation and Execution Design Digital Twins Definition Language (DTDL) The Digital Twins Definition Language (DTDL) is used to describe the physical twin. Each physical twin is encapsulated in a DTDL model, which is a JSON file that describes the properties and relationships. These DTDL models are then used to create digital twin instances in both PDTL and CDTL. Properties are used to store the states and changes of a particular digital twin by using basic property types or complex property types. The study only used basic property types, as these do not store complex values such as patient treatment details. Each DTDL model can then be used to establish relationships with other models. Due to limitations in the Azure Digital Twins platform, we used DTDL v2 to describe these instances and utilized the Azure SDK to perform create, read, update, and delete operations for digital twin instances and their relationships. Physical Digital Twins Layer (PDTL) We designed the Physical Digital Twins Layer (PDTL) and respective cohorts as Physical Digital Twin (PDT) in the framework based on means identified for gathering data. Due to time and scope limitations, only barcode readers were used in the study, referred to as IoT devices. The Unit PDT denoted by CCG Entity Code. We did not use the abbreviations which distinguishes other wards such as the Critical Care Unit (CCU) or Coronary Care Unit (CCU) for staff. Similar examples include Forrest Centre (FC) - Fracture Clinic (FC), Oncology Centre (OC) - Orthopaedics Children (OC), or single names such as Chiropody, Haematology, Pathology, etc. Additionally, the name length is limited to 1 KB and each name had to be unique. For that reason, the unit was named based on NHS guidelines as 78H rather than CCU or Critical Care Unit. Based on scalability, each Unit PDT is subdivided into Desktop PTDs which are host computers used to gather data. Desktop PDTs were identified by Desktop-{name of the host computer}, which were used to determine the data origin location. In this case, study used a unique identifier for the PC or the name of the IoT client application. The COM PDTs were added to PDTL to indicate which IoT devices are attached to each port. Rather than including this information as a property value inside the IoT device, it was added separately to identify whether the ports are enabled or disabled and to determine which COM ports are occupied by each wireless barcode reader. The IoT Device PDTs were named as CCU{device number}. This IoT Device PDT stored key data about the IoT device. Each IoT device is then attached to one of the COM ports, as illustrated in Fig. 4 . Session PDTs are temporary 30-second virtual sessions used to hold information from barcode readers. During the testing phase, we initially added timestamps with millisecond accuracy as S-{timestamp in milliseconds}. However, this approach was not sustainable in the real world, where events might occur in microseconds or nanoseconds apart. To create unique names for each digital twin, we decided to suffix a GUID as S-{GUID}. This solution addressed the uniqueness problem and avoided duplication issues even the data is ingested in nanoseconds apart. The main limitation of the barcode readers is their inability to process data within the device itself. Each telemetry event from the IoT Hub Client app contained a JSON object with the following structure. The IoT Hub client app sends the event to the ADT Ingestion in IoT Hub Event Grid Trigger Function App (uod-nhs-rns-rns01-78h-iot-hub-egt-fa/adt-ingestion) to create new sessions and update or replace values for existing valid sessions. The Session PDTs are used to store identifiers for patients, forms, or staff. These Session PDTs help to virtually store and queue relevant information and will be set expired if the properties within them are incomplete or expired. Each Session PDT stored and validated properties such as patient identifier, staff identifier, form identifier, start time, and end time. Once the Session PDT is valid, the property data is mapped to their conceptual twins, the Session PDT set expired, and a snapshot of this instance is stored in the SQL database for validation. Conceptual Digital Twins Layer (CDTL) The Conceptual Digital Twins Layer (CDTL) defines Conceptual Digital Twin (CDT) which is micro-ergonomic data such as rules, roles, processes, and standards twins of the Critical Care Unit (CCU). The data originates from the PDTL, and each snapshot is stored upon completion in a SQL database. The CDTL is interfaced with stakeholders, enabling interaction and generating reports through a web-based graphical user interface. As shown in Fig. 5 , the CDTL includes CDTs such as patient, form, task, activity, staff, and unit. Next, demand is created by patients when they are admitted to the unit for diagnosis and treatment. The staff, on the other hand, are equipped with process maps to follow for each patient based on specific criteria. The staff use different types of observation forms to record these diagnosis and treatment procedures for the patient. Subsequently, we were able to generate the framework for the CDTL by creating CDTs for these conceptual elements and mapping them based on the level of interaction using relationships. In this study, we did not store any patient-specific information or values from personal records. To denote the Patient CDT in the framework an increment value was suffixed to the Patient PDT ID as P-{increment number}, ensuring that each twin ID is unique in the CDTL. This patient ID value is derived from the Session PDT's Patient ID property. Then, the Form CDT was added to the CDTL to understand the frequency of each observation form type. The Form CDT helps define the type of treatment or diagnosis the Patient CDT is undergoing and assess the bed acuity level. The Form CDT is named with incremental values, such as F-{increment value}, which is an integer. Instead of using the full name of a form, such as "NGV1717 06/19 Individualised Care at the End of Life - Care Round Record Sheet (To be Used in Place of Enhanced Care Round Document)" we shortened it to the form ID F-50. This approach helped reduce errors and cleaned up the knowledge graph representation of the conceptual digital twins. These forms do not contain any patient-related data and are purely used to identify which form is used by the staff. The Task CDT is an instance of the Form CDT. In the real-world setting, each observation form is used by several staff members over a particular period. For example, the NGV1914 01/18 Critical Care Unit Daily Review observation form is used by clinicians and nurses to record observations such as heart rate or blood pressure and treatments such as medications prescribed for a patient. This form is allocated every 24 hours and is replaced with a new form at the end of the day. In the CDTL, this is considered a Task CDT. If a patient stays for 3 days, it means there are 3 Task CDTs. Each Task CDT is then attached to a Patient CDT and Form CDT recording the start and end times. This setup helps calculate bed acuity levels, costs per patient, the number of times a form has been used, and the average task completion time. The CDTL only allows one Task CDT for one Form CDT at any given instance, which helps identify work duplication and track ongoing tasks. The Task CDT was mapped using the Session PDT’s Patient ID, Form ID, and start/end timestamp properties. Each Task CDT included an "Is Task Completed" property which was used by staff to check if the task is completed or not. This resembled the process of changing observation forms in the physical setting. If there are no ongoing tasks, a new Task CDT will be created in CDTL. Further, the Action CDT is used to record individual sessions within a Task CDT. For example, the NGV1914 01/18 Critical Care Unit Daily Review form involves multiple interactions with doctors and nurses over its 24-hour period. These individual interactions are mapped to specific Action CDTs. Each Action CDT includes properties such as Is Action Completed, Start Timestamp, End Timestamp, Staff ID, and Task ID. When a staff member begins a treatment procedure, they first record the timestamp at the start of the procedure. They then record the second timestamp at the end of the procedure, which notifies the CDTL that the Action CDT has been completed. The CDTL enforces a rule that only one ongoing action is allowed for a specific task at a time by a staff member. Initially, a new Action CDT is created with both the start and end timestamps set to the same value. Once the action is completed, the end timestamp is updated, and the Is Action Completed property is set to true. This approach helps map individual staff interactions with a given task, calculate the time a staff member spends on an action, assess whether a particular staff member is busy, track the timeline of interactions with a patient, and evaluate the costs and efficiency of the treatment process for each patient at a more granular level. The Action CDT does not contain any patient-related data and is purely used to record timestamps. Next, the Staff CDT was used to identify staff members in the CDTL. The Staff CDT does not hold any personal data such as names, ages, or other personal details. Due to scope and time limitations, the study did not store user roles either. Each Staff CDT was named using the format S-{increment value}. The Staff CDT will be created if it does not already exist, and it will then be mapped to the relevant Action CDT based on the Task Id property of the Session PDT. Finally, the Unit CDT was used to map each staff member to their workstation. Currently, the CDTL mapping is used to map staff who work in the Critical Care Unit, specifically unit 78H. However, with scalability in mind future staff from cross-departmental interactions—such as scanning X-rays or blood checking—will be mapped based on available data to build a real-time, sophisticated knowledge graph representation of the hospital. Execution Software Infrastructure As shown in Fig. 6 , the IoT hub client application provided the interface to manage IoT devices. It established connectivity to the Azure cloud by dynamically generating symmetric keys for each IoT device using an HTTP endpoint. This endpoint was protected by Microsoft Defender for Cloud to identify malicious activities and Microsoft Entra to secure accessibility to endpoints and scopes. The app then retrieved symmetric keys to establish connectivity to the IoT hub Device Provisioning Service (DPS) dynamically based on the availability of devices. The cloud based digital twins interfaced with the humans using IoT devices and through a web interface. The dynamic nature of allocating cloud resources required flexibility, we used Azure Service Managers to allocate and generate security keys to establish connectivity between the aforementioned services in real-time. By using Function Apps and Event Grids, we captured the event data of IoT Hub and Digital Twins in SQL databases. The web interface provided users with accessibility to interact with these Digital Twins. A set of temporary emails were created using Entra to grant users access to the system. When staff scanned values using a barcode reader, the IoT Hub client created a telemetry event containing a JSON payload with information about the PC, IoT device, value, and timestamp. Each telemetry event was then filtered by the IoT hub Event Grid to trigger functions that to store this event data or ingested it into the PDTL based on their characteristics. Then a series of function apps were designed to capture these digital twins update events, on PDTL Event Grid triggers to modify the CDTL accordingly. The web-based dashboard provided an authenticated user interface for interacting with the Conceptual Twins, allowing users to generate reports such as identifying bed acuity, ongoing tasks and activities, costs by each form, costs by each patient, time taken by each form and staff member, and time spent on each patient. The study was limited in scope and did not build services such as notifying staff of ongoing activities or missing activities based on process maps. However, these potential expansions such as Time Triggers were identified and mentioned in the architecture for the future development. Hardware Infrastructure Due to computer privacy and security reasons, study did not use any computers connected to the existing NHS network or its private infrastructure. Instead, they used a custom-built PC to deploy the IoT hub client application and connect the IoT devices. This approach provided a greater control over their infrastructure and saved time by avoiding the need to obtain approval from the NHS to run a custom program on one of their. In the study, we used barcode readers (n = 3), specifically Tera 51000 Laser 1D (n = 2) and Tera D5100 2D (n = 1) wireless barcode scanners. Initially, the plan was to provide a scanner for each patient, but the constraints limited the number due to the coverage limitations of the barcode readers. The main wall dividing the east ward and west ward posed a significant barrier to establish connectivity between patients in farther sections with the IoT hub client application. Additionally, the glass walls separating each bed caused signal disruptions between the IoT client application and the IoT devices. Figure 5 shows the data points collected during the production phase, which helped create the coverage map displayed above. The map is not according to any scale but used in production to identify availability. Due to these challenges, the use of IoT devices was restricted to beds 6, 7, 8, and E, with bed D being vacant during the data collection period. Consequently, the study had to place a hybrid method that combined both offline and online approaches to collect data, utilizing paper forms and computers. Evaluation The consent forms were collected from the participants doctors (n = 15) and nurses (n = 5) at the Critical Care Unit of Northampton General Hospital NHS Trust. These consent forms were generic, not specific to reference what type of information gathered or type of task they performed during the study. Each patient and staff were identified by using custom numbers during the data collection, which was only used by the staff to track the tasks performed for each patient. Any staff and patient specific data were not collected during the study. Offline The offline method was deployed to overcome network issues caused by barriers between patients and the IoT hub client application. This method, staff member could use either IoT devices or simply write on the paper the start and end times. Later on, the data points written on the form were added to the digital twins framework using the online method. Online First, temporary emails were provided to each staff member to access the system through the web interface. Each barcode was assigned to a patient to allow staff to gather start and end times efficiently. This system helped track patients when they were moved to other beds based on the severity of their condition. The online method was primarily limited to those who already had access to computers. The online interface featured three user roles: managers, administrators, and staff. The Fig. 8 given below shows the web-based dashboard designed for staff. Moreover, based on the data collected in the digital twins, unit managers could generate reports such as average time and costs related to each patient, bed acuity levels at a given time, and the costs generated by forms. Administrators could manage staff member access, create new users, oversee overall resource usage, allocate IoT devices to patients, and manage resources. The staff interface allows users to create, read, and update digital twins, allocate resources, monitor bed acuity levels, track ongoing tasks and actions for respective staff members, mark tasks or actions as complete, and create new actions based on forms. Dataset The dataset was extracted using the Digital Twins Query Language from Digital Twins Instances. Each event did not contain any data related to patients or staff, but rather workflows at the CCU. This data included the start and end timestamps of actions, observation form types, and the digital twins' names for staff and patients. We cleaned the data in the digital twins instances into generalized records, showing the number of minutes spent on each task, categorized by process groups. The dataset is not publicly accessible and is attached as a supplementary file for review purposes. Declarations Data Availability Current datasets generated during the study are attached with supplementary files and review only. Once get accepted we can me it available for the public access. Code Availability The underlying repositories used in this study are not publicly available for proprietary reasons. We will make some parts of the framework's source code available to the public in the next phases. Author Contributions GK implemented the digital twins framework on Azure Cloud and co-authored the discussion, methods, and data and code availability sections. MH drafted the overall manuscript and contributed to the design of the digital twin for CCU. MZ developed process maps, addressed domain-specific aspects of the framework, and co-authored the abstract, introduction, and discussion sections. WAK assisted in reviewing and refining the manuscript. GK, MH, and MZ contributed equally and should be recognized as co-lead authors. Acknowledgments This project was funded by TechTach Limited and the University of Derby under a joint collaboration agreement (internal project ID: PSL2324-0100). The authors also express their gratitude to the staff members of CCU at Northampton General Hospital, who voluntarily provided domain knowledge and participated in the Digital Twin usage trials. Competing Interests The authors declare that no competing of financial interests. References Wright, L. & Davidson, S. How to tell the difference between a model and a digital twin. Adv Model Simul Eng Sci 7 , (2020). Surian, N. U. et al. A digital twin model incorporating generalized metabolic fluxes to identify and predict chronic kidney disease in type 2 diabetes mellitus. NPJ Digit Med 7 , 140 (2024). Chu, Y., Li, S., Tang, J. & Wu, H. The potential of the Medical Digital Twin in diabetes management: a review. Front Med (Lausanne) 10 , (2023). Walsh, J. R., Roumpanis, S., Bertolini, D. & Delmar, P. Evaluating Digital Twins for Alzheimer’s Disease using Data from a Completed Phase 2 Clinical Trial. Alzheimer’s & Dementia 18 , (2022). Corral-Acero, J. et al. The ‘Digital Twin’ to enable the vision of precision cardiology. Eur Heart J 41 , 4556–4564 (2020). Lin, T.-Y. et al. Assessing overdiagnosis of fecal immunological test screening for colorectal cancer with a digital twin approach. NPJ Digit Med 6 , 24 (2023). Scott, A. K. & Oyen, M. L. Virtual pregnancies: predicting and preventing pregnancy complications with digital twins. Lancet Digit Health 6 , e436–e437 (2024). Jin, Z. et al. Anti- and pro-fibrillatory effects of pulmonary vein isolation gaps in human atrial fibrillation digital twins. NPJ Digit Med 7 , 81 (2024). Laubenbacher, R., Sluka, J. P. & Glazier, J. A. Using digital twins in viral infection. Science vol. 371 Preprint at https://doi.org/10.1126/science.abf3370 (2021). Podéus, H. et al. A physiologically-based digital twin for alcohol consumption—predicting real-life drinking responses and long-term plasma PEth. NPJ Digit Med 7 , 112 (2024). Voigt, I. et al. Digital Twins for Multiple Sclerosis. Front Immunol 12 , (2021). Hansen, J., Jain, A. R., Nenov, P., Robinson, P. N. & Iyengar, R. From transcriptomics to digital twins of organ function. Front Cell Dev Biol 12 , (2024). Li, X. et al. A dynamic single cell-based framework for digital twins to prioritize disease genes and drug targets. Genome Med 14 , 48 (2022). Gazerani, P. Intelligent Digital Twins for Personalized Migraine Care. J Pers Med 13 , 1255 (2023). Corral-Acero, J. et al. The ‘Digital Twin’ to enable the vision of precision cardiology. Eur Heart J 41 , 4556–4564 (2020). Katsoulakis, E. et al. Digital twins for health: a scoping review. NPJ Digit Med 7 , 77 (2024). Tresfon, J., Brunsveld-Reinders, A. H., Van Valkenburg, D., Langeveld, K. & Hamming, J. Aligning work-as-imagined and work-as-done using FRAM on a hospital ward: a roadmap. BMJ Open Qual 11 , (2022). Alyahya, M. S. et al. The association between cognitive medical errors and their contributing organizational and individual factors. Risk Manag Healthc Policy 14 , (2021). Illingworth J et al. The National State of Patient Safety: What We Know about Avoidable Harm in England . (2022). Ahsani-Estahbanati, E., Doshmangir, L., Najafi, B., Akbari Sari, A. & Sergeevich Gordeev, V. Incidence rate and financial burden of medical errors and policy interventions to address them: a multi-method study protocol. Health Serv Outcomes Res Methodol 22 , 244–252 (2022). Organization, W. H. Global Patient Safety Report 2024 . (World Health Organization, Geneva, 2024). The Faculty of Intensive Care Medicine (FICM) & Intensive Care Society (ICS). Guidelines for the Provision of Intensive Care Services (GPICS). GPICS v2.1 https://www.ficm.ac.uk/standards/guidelines-for-the-provision-of-intensive-care-services (2022). NHS England. A just culture guide. https://www.england.nhs.uk/patient-safety/patient-safety-culture/a-just-culture-guide/. Carayon, P., Wooldridge, A., Hoonakker, P., Hundt, A. S. & Kelly, M. M. SEIPS 3.0: Human-centered design of the patient journey for patient safety. Appl Ergon 84 , (2020). Jalali, M., Dehghan, H., Habibi, E. & Khakzad, N. Application of “Human Factor Analysis and Classification System” (HFACS) Model to the Prevention of Medical Errors and Adverse Events: A Systematic Review. International Journal of Preventive Medicine vol. 14 Preprint at https://doi.org/10.4103/ijpvm.ijpvm_123_22 (2023). Kaushik, P., Rao, A. M., Singh, D. P., Vashisht, S. & Gupta, S. Cloud Computing and Comparison based on Service and Performance between Amazon AWS, Microsoft Azure, and Google Cloud. in Proceedings of International Conference on Technological Advancements and Innovations, ICTAI 2021 (2021). doi:10.1109/ICTAI53825.2021.9673425. Kherbache, M., Maimour, M. & Rondeau, E. Digital Twin Network for the IIoT using Eclipse Ditto and Hono. in IFAC-PapersOnLine vol. 55 (2022). Grieves, M. Origins of the Digital Twin Concept . (2016). doi:10.13140/RG.2.2.26367.61609. Bisanti, G. M., Mainetti, L., Montanaro, T., Patrono, L. & Sergi, I. Digital twins for aircraft maintenance and operation: A systematic literature review and an IoT-enabled modular architecture. Internet of Things 24 , 100991 (2023). Jiang, Y. et al. Multi-domain ubiquitous digital twin model for information management of complex infrastructure systems. Advanced Engineering Informatics 56 , 101951 (2023). Madusanka, N. S., Fan, Y., Yang, S. & Xiang, X. Digital Twin in the Maritime Domain: A Review and Emerging Trends. J Mar Sci Eng 11 , 1021 (2023). Tao, F., Zhang, H. & Zhang, C. Advancements and challenges of digital twins in industry. Nat Comput Sci 4 , 169–177 (2024). Singh, M. et al. Digital Twin: Origin to Future. Applied System Innovation 4 , 36 (2021). Geoffrey Chase, J. et al. Digital Twins in Critical Care: What, When, How, Where, Why? IFAC-PapersOnLine 54 , 310–315 (2021). Minerva, R. & Crespi, N. Digital Twins: Properties, Software Frameworks, and Application Scenarios. IT Prof 23 , 51–55 (2021). Awill, R., Khan, W. A., Hussain, M., Zada, S. & Anderson, B. Aerospace Qualification Services Knowledge Graph: A Leap towards Enhanced Data Management. in CEUR Workshop Proceedings vol. 3632 (2023). Additional Declarations No competing interests reported. Supplementary Files DT4CCUSupplementaryInformation202408v1.pdf Cite Share Download PDF Status: Published Journal Publication published 19 Jun, 2025 Read the published version in npj Digital Medicine → Version 1 posted Editorial decision: Revision requested 30 Dec, 2024 Reviews received at journal 18 Dec, 2024 Reviews received at journal 08 Dec, 2024 Reviewers agreed at journal 05 Dec, 2024 Reviewers agreed at journal 30 Nov, 2024 Reviewers agreed at journal 29 Nov, 2024 Reviews received at journal 21 Oct, 2024 Reviewers agreed at journal 16 Oct, 2024 Reviewers invited by journal 15 Sep, 2024 Editor assigned by journal 02 Sep, 2024 Submission checks completed at journal 02 Sep, 2024 First submitted to journal 31 Aug, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5010353","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":361368677,"identity":"de277de3-68f9-4408-bdbd-693fd3eeead6","order_by":0,"name":"Gayan Dihantha Kuruppu Kuruppu Appuhamilage","email":"","orcid":"","institution":"University of Derby","correspondingAuthor":false,"prefix":"","firstName":"Gayan","middleName":"Dihantha Kuruppu Kuruppu","lastName":"Appuhamilage","suffix":""},{"id":361368678,"identity":"2cf1d8c7-ec03-433d-999d-8e95dc92ff52","order_by":1,"name":"Maqbool Hussain","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYFACHijJ3mDAwNgAEYPRBLTwHCBRCwODRAKRWnQbeI9J/vhjJ2Mu+Xjj48odhxn42w+wSc7Ao8XsAF+aNG9bMo/l7LRiw7NnDjNInElgk9yAVwuPmTRjAzOPwe0cM8nGtsMMDDcY2CQfENACdFg9j8HNM+Y/QVrkidEiwcN2mMfgBo8ZI0iLAUgLXocd5jG25m07zmNwJq1YsvFMOo/hmcRmS7zeP95jePPHn2p7g+OHN35s3GEtJ3f88MGbPXi0MDCjcpt5CEYkOqgjSfUoGAWjYBSMDAAApdtK5FZhjgEAAAAASUVORK5CYII=","orcid":"","institution":"University of Derby","correspondingAuthor":true,"prefix":"","firstName":"Maqbool","middleName":"","lastName":"Hussain","suffix":""},{"id":361368679,"identity":"6d798bf6-96d5-4105-a11b-ff6f53c0956f","order_by":2,"name":"Mohsin Zaman","email":"","orcid":"","institution":"Northampton General Hospital NHS Trust","correspondingAuthor":false,"prefix":"","firstName":"Mohsin","middleName":"","lastName":"Zaman","suffix":""},{"id":361368680,"identity":"e503e0db-9300-4848-8a7b-880369d5e64d","order_by":3,"name":"Wajahat Ali Khan","email":"","orcid":"","institution":"University of Derby","correspondingAuthor":false,"prefix":"","firstName":"Wajahat","middleName":"Ali","lastName":"Khan","suffix":""}],"badges":[],"createdAt":"2024-08-31 19:23:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5010353/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5010353/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41746-025-01738-4","type":"published","date":"2025-06-19T15:57:19+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":66950956,"identity":"d42af84e-2124-481d-9357-14de16c13392","added_by":"auto","created_at":"2024-10-18 10:22:14","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":195704,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eClassification of data in healthcare sector.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/a0a355ac0bbbf607351834e4.jpg"},{"id":66950554,"identity":"8652ee22-f586-47e1-ad0d-4aa6d41f3562","added_by":"auto","created_at":"2024-10-18 10:14:14","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":253666,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFour-step model of the framework.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure2Fourstepmodeloftheframework.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/97622d28f1e154da45588112.jpg"},{"id":66950556,"identity":"09aa5e5f-173c-4e15-865a-1cb1ca0690fd","added_by":"auto","created_at":"2024-10-18 10:14:14","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":212775,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe process map of the patient admission\u003c/strong\u003e.\u003c/p\u003e\n\u003cp\u003eThe above process map is one of the many processes we have identified in the CCU. These process maps were created for structured workflows to identify resource consumption and interactions with each resource. These maps helped non-medical domain users. The above process map involves admitting a patient to the CCU. This shows the type of bedspace required, preadmission checks, forms, procedures, and handover. This helped to identify the types of observation forms used to record patient data, staff roles interacting in each stage, and workflow of the admission process.\u003c/p\u003e","description":"","filename":"Figure3Processmapofthepatientadmission.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/124aab97c948be0a06c8c970.jpg"},{"id":66950562,"identity":"bfddad9e-1a8e-401c-84dd-8651ef517956","added_by":"auto","created_at":"2024-10-18 10:14:15","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":109991,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe knowledge graph representation of Physical Digital Twins (PDT) and relationships\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"Figure4TheknowledgegraphrepresentationofPhysicalDigitalTwinsPDTandrelationships.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/c39b853d8a13605735f4de3c.jpg"},{"id":66952654,"identity":"ce278022-d651-45cc-a2cb-62ca9c738a46","added_by":"auto","created_at":"2024-10-18 10:38:17","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":156950,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe knowledge graph representation of Conceptual Digital Twins (CDT) and relationships\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"Figure5TheknowledgegraphrepresentationofConceptualDigitalTwinsCDTandrelationships.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/6497dbafb96d2d6216c74aa8.jpg"},{"id":66951947,"identity":"a575a4dc-813a-43a6-88df-a21e93b8705e","added_by":"auto","created_at":"2024-10-18 10:30:14","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":235270,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eOverview of the cloud architecture used in the study\u003c/strong\u003e.\u003c/p\u003e","description":"","filename":"Figure6Overviewofthecloudarchitectureusedinthestudy.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/4ca02d8e8077756cbc68d73b.jpg"},{"id":66950957,"identity":"68c5cae2-5e33-4314-b567-46b1c3fe839b","added_by":"auto","created_at":"2024-10-18 10:22:14","extension":"jpg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":204638,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eData collection using offline method\u003c/strong\u003e.\u003c/p\u003e\n\u003cp\u003eA) A system-generated staff ID was created for each staff member, linked to a barcode.\u003c/p\u003e\n\u003cp\u003eB) A list of forms categorized by process groups was distributed to each staff member, allowing them to choose between using the online or offline method. Staff members could either record the start and end times of their actions manually or use barcode readers.\u003c/p\u003e\n\u003cp\u003eC) Due to privacy concerns, the authors did not use any real patient identification. Instead, each patient was assigned an incremental value, which was printed on a form. Each barcode reader was then assigned to an available patient based on connectivity, effectively mapping the barcode reader to the patient. This approach reduced the number of times a staff member had to record the time from three to two instances.\u003c/p\u003e","description":"","filename":"Figure7Datacollectionusingofflinemethod.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/d513ac4195e9d0b25a56986c.jpg"},{"id":66950559,"identity":"37db7113-cf40-4525-8447-923b2c2e5ebe","added_by":"auto","created_at":"2024-10-18 10:14:14","extension":"jpg","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":191824,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eData collection using the online method\u003c/strong\u003e.\u003c/p\u003e\n\u003cp\u003eA) We used Microsoft Entra to generate custom emails for logging into the system. Each email was assigned with the staff member's first name to make it easily readable when they logged into the web UI. The web GUI was automatically enabled with Microsoft login, which was saved in their browser and authenticated using a password or the Microsoft Authenticator app, making it secure and familiar to use. We provided them with a temporary password, which they were required to change later.\u003c/p\u003e\n\u003cp\u003eB) The login screen displays additional login options such as custom email or password, default Microsoft authentication, and Google authentication.\u003c/p\u003e\n\u003cp\u003eC) The authentication screen appears before users accesses the dashboard.\u003c/p\u003e\n\u003cp\u003eD) The dashboard contains the user interface for interacting with the conceptual digital twins.\u003c/p\u003e","description":"","filename":"Figure8Datacollectionusingonlinemethod.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/bf740bbd51e34410656f4b37.jpg"},{"id":85231332,"identity":"8941a132-5c80-43a4-ad62-e8ed85cdf86f","added_by":"auto","created_at":"2025-06-23 16:06:16","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3675347,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/53a97338-aa27-4b37-b6c2-a09321e137c5.pdf"},{"id":66950563,"identity":"69d2f278-66b0-4b3e-b15d-c41535b327ff","added_by":"auto","created_at":"2024-10-18 10:14:15","extension":"pdf","order_by":21,"title":"","display":"","copyAsset":false,"role":"supplement","size":24702690,"visible":true,"origin":"","legend":"","description":"","filename":"DT4CCUSupplementaryInformation202408v1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5010353/v1/ce0d584205b9bf9908bd1f34.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DT4CCU – A Digital Twins framework for Critical Care Unit","fulltext":[{"header":"Introduction","content":"\u003cp\u003eThe primary objective of the proposed framework is to explore how the foundation for precision medicine can be effectively established and integrated into clinical practice. To achieve this, it is essential to gain a clear understanding of the interactions between healthcare providers and patients, the complexities of disease models, and the design of the healthcare system itself. By examining these factors, we aim to identify the critical elements that must be addressed and optimized to successfully implement precision medicine in routine clinical settings. To achieve this aim, we concluded that the most effective approach to collecting and interpreting data on these interactions would be through the design of a digital twin, as it can handle the design of object, evolution of the data related to the object, and changes in the model based on the evolving data\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. Legacy work (predicting Type 2 Diabetes Mellitus by modelling generalized metabolic fluxes\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e and diabetes management\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e, Alzheimer\u0026rsquo;s disease\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e, cardiovascular diseases\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e, colorectal cancer\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e, preventing complications in pregnancy\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e, human atrial fibrillation\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e, viral infection\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e, alcohol consumption\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e, multiple Sclerosis\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e, simulating cells, organs\u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e, genes and drug discovery\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e, migraine care\u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e, and enabling precision cardiology15) on digital twins for health (DT4H)\u003csup\u003e\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e primarily focuses directly on patients, specifically targeting the diagnosis and treatment of specific diseases or medical conditions rather than how the activities were performed.\u003c/p\u003e \u003cp\u003eThe use of digital twin in health domain is primarily because the problem lies with the fact that a lot of the information that\u0026rsquo;s collected, structured and then acted upon requires human expertise which directly leads to a significant gap between how activity is imagined and how it\u0026rsquo;s performed\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u003c/sup\u003e; which is to say that we need to know what is happening as opposed to what should happen. This will need a system which can track activity in real time and develop some insight for the user into how the information is to be presented and acted upon. Therefore, digital twin is the most practical solution to bridge the gap between work as imagined and work as done.\u003c/p\u003e \u003cp\u003eLooking at how work is done, we know that Cognitive tasks contribute significantly to medical errors\u003csup\u003e\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e, an essential component of a preventative strategy would be to intervene before judgements are made. A management strategy no matter how good, if based on flawed assumptions is likely to be flawed. So, when it comes to actions, they can be classified as structured (i.e. rolling a patient in a bed or taking blood pressure- the task has a step-by-step process, demand and frequency are well defined. The other type of actions is unstructured, these are tasks like taking a history and planning. Here the sequence of questions, the focus of examination and investigations ordered can differ from patient to patient even if they have the same presenting complaint.\u003c/p\u003e \u003cp\u003eSince healthcare system are reliant on human beings, we needed to see how humans behave in any given work environment, how they perform activities and what might lead to error. So, introduction of human factors into both system and process design as well as an incident analysis became an essential part of the proposed framework. Patient Safety is the lens-through which all these interactions are analysed and so it became a core objective of how we design our digital twin became A tantamount objective in design and implementation of this framework as well as the most practical approach to introducing a digital twin into a healthcare environment.\u003c/p\u003e \u003cp\u003eThe other thing unique to healthcare care from a digital twin perspective is that it\u0026rsquo;s a system in flux, The demands on the services and structures are constantly changing, as new components are added, and old ones discarded the twin would need to have the ability to reflect these and incorporate these changes without significant labour to reflect the change. This would mean that the people involved with service design need familiarity with how the service structures are displayed and associations made. Part of the prediction is not only how health care outcomes would change, but what would any change mean in terms of cost and benefit. The other problem with change is understanding associations. Emergence in complicated systems would be of particular importance in healthcare twin.\u003c/p\u003e \u003cp\u003eThe state of patient safety report 2022\u003csup\u003e19\u003c/sup\u003e stated that the cost of medication error alone is around 98\u0026nbsp;million pounds, yet when you look at the cost in terms of clinical negligence claims its 7.9\u0026nbsp;billion pounds for the year 2020/21. In the USA the cost of medical error is around 20\u0026nbsp;billion Dollars Annually\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e. In any such system, anything which might be able to help with prediction of errors and more importantly help prevent errors before they occur would be of huge benefit for both workers and service users (patients). We can also see that our Digital twin-based framework approach will align ideally with the objectives of the global patient safety initiative\u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eOnce we had decided on the focus of our project, the next issue was agreed on how meaning would be given to the collected data. This meant looking at the needs of the roles that would engage with the data to make sure the data collected is structured. It is anticipated that as time progresses, the modalities would change, the weightage of collected data would change or give new insights, as we see population drifts and as we see alteration in health seeking behaviour, we would see the implications of these in interpretation and planning of interventions. Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e below shows a graphical chart of the classification of healthcare data for digital twins.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eWith a clear way forward, we needed to see which specialty would be best to trial and validate our concepts in. We needed a cohort not limited by a specific disease type, was accustomed to collecting large amounts of data, had well prescribed management pathways independent of specific pathology and well-structured systems and process thinking embedded into his existing management pathways. The critical care unit thus appeared an ideal location to start applying the proposed framework.\u003c/p\u003e \u003cp\u003eWe started by looking at the Guidelines for Provision of Critical Care Services (GPICS)\u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e. We identified that there would be anywhere between 10 to 30 people with distinct roles who might be in contact with a patient on any given day, depending on the stage of their journey though the admission process. We gathered and reviewed all the existing documentation for each of these roles and then developed process maps around specific roles, as well as around the patient themselves.\u003c/p\u003e \u003cp\u003eThe framework is structured into the following phases.\u003c/p\u003e \u003cp\u003ePhase 1(Real-Time Activity Tracking): Can the proposed framework tract activity live?\u003c/p\u003e \u003cp\u003ePhase 2 (Workflow Integration and Benchmarking): Can it embed data collection strategy into existing workflows? (with clinical and governance workflows as an example) and can we compare that against a standard?\u003c/p\u003e \u003cp\u003ePhase 3 (Behavioural and Decision Support) : Can behaviour modification and decision support tools be introduced into practice? (with a focus on Bias \u0026amp; Noise around decision making)\u003c/p\u003e \u003cp\u003ePhase 4 (CCU Insights and Scenario Simulation): Can the twin be used to implement an overall management strategy on a unit, by giving insights into system strengths and vulnerabilities and be used to scenario-based simulations?\u003c/p\u003e \u003cp\u003ePhase 5 (Scaling and Interdepartmental Integration): Can the proposed framework scale for joining up of different departments of a hospital/ Health system with their own digital twins.\u003c/p\u003e \u003cp\u003eFeasibility study for Phase 1 and groundwork for phase 2 has been completed, we have looked at incident analysis as it exists currently and how it would look with implementation and incorporation of just culture\u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e and SEIPS 3.0\u003csup\u003e24\u003c/sup\u003e model and HFACS\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e classification into both the data collection strategy for incidence reporting \u0026amp; analysis. This we hope will help inform both the contributing factors as well as inform a mitigation strategy to prevent future incidents.\u003c/p\u003e \u003cp\u003eThe objectives laid for the phases have been realized with the proposed framework, Digital Twins Framework for Critical Care Unit (DT4CCU). The framework is designed using a layered approach, as it allows decoupling which ultimately helped to replicate the physical elements of the critical care unit in a Physical Digital Twin (PDT). Based on the PDT, the micro-ergonomic characteristics were then mapped to Conceptual Digital Twin (CDT). This novel approach helped to minimize the dependency between the physical elements with the actual workflow. Subsequently, this approach helped realization with increasing the reusability, testability, and refactorability of the framework.\u003c/p\u003e \u003cp\u003eThe primary motivation for leveraging this technology is to create a virtual replica of the critical care unit, enabling the organization of physical twins within complex structures through a digital overlay. The framework currently utilized Microsoft Azure because of its compatibility with Windows based NHS systems. The usage of other platforms such as Amazon Web Services (AWS), Google Cloud Platform (GCP)\u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e and open-source frameworks such as Eclipse Hono\u0026thinsp;+\u0026thinsp;Ditto\u003csup\u003e27\u003c/sup\u003e and others will be investigated and adapted in future to validate the framework\u0026rsquo;s portability. Azure also supports event-driven programming methodologies, facilitating applications like historical data recording and service triggers while providing a secure and reliable service. This enabled the development of service triggers based on changes to the physical twins and historical data allowing for real-time prediction of workflows such as potential malfunctions within the treatment process or work duplication. Subsequently these technologies were facilitated with capability to develop programs to notify the relevant personnel through bi-directional communication between the physical and digital twins. The PDTs and CDTs helped to lay the foundation for implementing a digital twin system to bridge the gap between work as perceived and work as done, to determine where clinicians are, where they want to be, and how they can get there when making a diagnosis and treating diseases, thereby reducing the risks of patient deaths and supporting staff during the diagnosis and treatment process.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eDomain Perspective\u003c/p\u003e \u003cp\u003eThe information that was taken out from the Critical Care Unit (CCU) at Northampton General Hospital NHS Trust, Cliftonville, Northampton NN1 5BD. The setup consisted of 14 staff members with 10 patients over 7 days. During the study, the framework was evaluated by using takt-time analysis with the data collected from doctors(n\u0026thinsp;=\u0026thinsp;11) and nurses(n\u0026thinsp;=\u0026thinsp;3). The average, minimum, maximum, and count functions applied for each process group are shown for doctors in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e (daily entries tasks) and for nurses in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e (peri-operative tasks), Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e (procedure lines tasks), and Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e (admission tasks). Due to a lack of data reported during the data collection period task group 2 (medical diseases) and task group 5 (death and dying) were not summarized as tables, as given below. Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e in the methods section shows all the tasks categorized by process groups for reference.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTime (minutes) spent by doctors to perform daily entries tasks.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFunction\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eF-18\u003c/p\u003e \u003cp\u003e(Clinical Notes)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eF-31\u003c/p\u003e \u003cp\u003e(Critical Care Unit Prescription and \u003c/p\u003e \u003cp\u003eAdministration Record)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF-34\u003c/p\u003e \u003cp\u003e(Critical Care Patient and Family \u003c/p\u003e \u003cp\u003eCommunication Record)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eF-42\u003c/p\u003e \u003cp\u003e(Treatment Escalation Plan (TEP) To be \u003c/p\u003e \u003cp\u003ecompleted for all patients)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eF-58\u003c/p\u003e \u003cp\u003e(Critical Care Unit Daily Review)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eF-91\u003c/p\u003e \u003cp\u003e(Invasive Procedure Safety Checklist: \u003c/p\u003e \u003cp\u003eCVC/Dialysis Catheter/PICC Insertion)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eF-109\u003c/p\u003e \u003cp\u003e(Procedure Intubation)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eTime taken to perform daily entries tasks\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e19.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e12.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e88.76\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e65\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMax\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e115\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCount\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTime (minutes) spent by nurses to perform peri-operative tasks.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFunction\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eF-37 (Trust Core Neurovascular Limb Assessment (Adult))\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eF-66 (Summary of Wound Care)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTime taken to perform peri-operative tasks\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.50\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMax\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCount\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTime (minutes) spent by nurses to perform procedure lines tasks.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFunction\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eF-6\u003c/p\u003e \u003cp\u003e(Trust Peripheral Venous Cannula \u003c/p\u003e \u003cp\u003e(PVC) Care Plan (Adult))\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eF-9\u003c/p\u003e \u003cp\u003e(Wound Care Plan)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF-10\u003c/p\u003e \u003cp\u003e(Trust Core Care Plan and Risk Assessment for Patients with Nasogastric Feeding Tube (Adult))\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eF-12\u003c/p\u003e \u003cp\u003e(Trust Core Care Plan Care of the Patient with an Indwelling Urinary \u003c/p\u003e \u003cp\u003eCatheter (Adult))\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eF-32\u003c/p\u003e \u003cp\u003e(Trust Critical Care Arterial Cannula \u003c/p\u003e \u003cp\u003e(AC) Care Plan)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eTime taken to perform procedure lines tasks\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e9.40\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMax\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCount\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTime (minutes) spent by nurses to perform admission tasks.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFunction\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eF-5\u003c/p\u003e \u003cp\u003e(Trust Bedrail Assessment and Core \u003c/p\u003e \u003cp\u003eCare Plan (Adult))\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eF-35\u003c/p\u003e \u003cp\u003e(Food Record Chart Nutrition and Diabetic Services)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF-63\u003c/p\u003e \u003cp\u003e(Critical Care Nursing Assessments \u003c/p\u003e \u003cp\u003eand Care Plans)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eF-77\u003c/p\u003e \u003cp\u003e(Critical Care Patient Property Form)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eF-113\u003c/p\u003e \u003cp\u003e(Trust Core Patient Activities of Daily \u003c/p\u003e \u003cp\u003eLiving - Initial Assessment)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eTime taken\u003c/p\u003e \u003cp\u003eto perform\u003c/p\u003e \u003cp\u003eadmission\u003c/p\u003e \u003cp\u003etasks\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e23.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e33.33\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMin\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e20.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMax\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e25.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCount\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eRouting (integers) and Event Grid latency (milliseconds) of the Azure IoT Hub.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTimestamp\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTelemetry messages sent (Sum)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eEvent Grid deliveries (Sum)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRouting: message latency for messages/events (Avg)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eEvent Grid latency (Avg)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e149.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e179.39\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e208.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e237.42\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e188\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e188.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e155.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e190.39\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e166.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e213.25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e164.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e206.41\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e150.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e185.14\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e166.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e173.56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e181.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e197.33\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e147.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e175.29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e148.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e159.37\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e208.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e202.60\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e24/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e203\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e198\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e25/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e234\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e183.80\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e26/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e186.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e173.83\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e181.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e234\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e162\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e181.50\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. \u003cb\u003eTime (minutes) spent by doctors to perform daily entries tasks.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. \u003cb\u003eTime (minutes) spent by nurses to perform peri-operative tasks.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. \u003cb\u003eTime (minutes) spent by nurses to perform procedure lines tasks.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. \u003cb\u003eTime (minutes) spent by nurses to perform admission tasks.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eFirst, the daily entries process group by doctors included n\u0026thinsp;=\u0026thinsp;11 shifts. Out of 22 tasks, only 7 tasks were reported during the data collection period. The F-58 (Critical Care Unit Daily Review) and F-18 (Clinical Notes) were frequently used in each shift. As previously identified by the domain experts, Critical Care Daily Review took on average 6 minutes to perform. The F-109 (Procedure Intubation) task had the lowest variability with an average of 12.5 minutes. Additionally, doctors took an average of 88.76 minutes to perform tasks in the daily entries process group.\u003c/p\u003e \u003cp\u003eSecond, the peri-operative process group by nurses was recorded only during 2 shifts, which included 6 tasks, but only 2 were reported. Tasks included in the process group but not recorded were F-24 (Peri-operative Care Pathway), F-25 (Trust Core Care Plan Colostomy/Ileostomy), F-38 (Assessment to be carried out before elective surgery and/or endoscopy to identify patients with or at increased risk of OCJ or vCJD), and F-105 (Maintenance Check List Faecal Collection System). Nurses took an average of 3.5 minutes to perform peri-operative tasks, with a variability of 0.5 minutes.\u003c/p\u003e \u003cp\u003eThird, the procedure lines process group recorded data from 5 shifts, and out of 13 tasks, only 5 were reported during the data collection period. The following tasks were included in the process group but not recorded: F-16 (Adult Acute Pain Service Patient Controlled Analgesia), F-46 (Trust Core Care Plan: Tracheostomy (Adult)), F-53 (Adult Transfusion Prescription and Administration Record), F-54 (Diabetic Ketoacidosis (DKA) Management for Adults), F-56 (Intravenous Heparin Chart), F-72 (Critical Care Therapies Treatment Record), F-84 (Critical Care Continuous Renal Replacement Therapy Prescription Form \u0026amp; Chart for Citrate), and F-97 (MRI Patient Screening Questionnaire and Consent Form). The F-6 (Trust Peripheral Venous Cannula (PVC) Care Plan (Adult)), F-12 (Trust Core Care Plan Care of the Patient with an Indwelling Urinary Catheter (Adult)), and F-32 (Trust Critical Care Arterial Cannula (AC) Care Plan) tasks were recorded in every process group, with averages of 2, 1.4, and 2 minutes each. Overall, nurses took an average of 9.4 minutes to perform procedure lines tasks, with a minimum of 7 minutes and a maximum of 13 minutes.\u003c/p\u003e \u003cp\u003eFinally, the admission process group recorded data from 4 shifts, with data recorded for 6 out of 9 tasks. The tasks F-14 (Trust Pain Assessment Tool and Core Care Plan for Patients with Learning Disabilities (Adults) and Patients who have Dementia or Cognitive Impairment), F-24 (Peri-operative Care Pathway), and F-101 (Parenteral Nutrition: Initial Review Form) did not record any data during the data collection period. On average, it took 34.33 minutes to complete an admission process group.\u003c/p\u003e \u003cp\u003eFrom the domain perspective, data collection was integrated as an additional task within the existing workflow. This led to staff members spending less time on tasks such as the F-5 (Trust Bedrail Assessment and Core Care Plan (Adult)) during the admission process, even though these tasks typically require more time due to the busy nature of shift hours. In practice, these tasks often took more than one minute to complete. It was observed that staff members would log the start and end times for these tasks at their initiation, rather than upon completion, which did not reflect the actual time taken.\u003c/p\u003e \u003cp\u003eOn average, doctors took 88 minutes to complete their daily entries, with significant variation ranging from 65 to 115 minutes. In contrast, nurses spent 3 to 4 minutes on perioperative tasks, 7 to 13 minutes on procedure lines, and 30 to 35 minutes on admission tasks, showing less variation. This difference is attributed to doctors primarily performing unstructured tasks, whereas nurses engage in more structured tasks.\u003c/p\u003e \u003cp\u003eTechnology Perspective\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e below shows the routing and event grid latencies of the IoT Hub from the data collection period from 2024/06/20 to 2024/06/27. During this period, the highest recorded telemetry events were 79 on 2024/06/23, and the lowest were 3 on 2024/06/24 and 2024/06/27. The routing latency fluctuated, ranging from 149 milliseconds to 208 milliseconds, and the event grid latency ranged from 179 milliseconds to 237 milliseconds. The number of telemetry events corresponds to the latencies, but factors such as the size of the telemetry payload and the time between two telemetry events were also could cause to higher latencies. Due to a lack of data recorded during the data collection period, some rows were removed from the table.\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e. \u003cb\u003eRouting (integers) and Event Grid latency (milliseconds) of the Azure IoT Hub.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e below shows the latency data for two Digital Twins instances during the period from 2024/06/20 to 2024/06/27, recording average latency data in milliseconds for API requests and routing operations. The physical Digital Twins instance recorded the highest latency at 208.5 milliseconds on 2024/06/26 and the lowest at 12.508 milliseconds on 2024/06/20. The routing latencies were variable, with the highest recorded latency being 399.403 milliseconds on 2024/06/23 and the lowest latency being 32.226 milliseconds on 2024/06/20. The conceptual Digital Twins instance recorded an average API request latency of 338.213 milliseconds on 2024/06/23 and the lowest at 23.861 milliseconds. The routing latency for the conceptual instance varied, with the highest recorded at 221.364 milliseconds on 2024/06/27 and the lowest at 102.357 milliseconds on 2024/06/23. Both Digital Twins instances showed variability in latency, with both instances recording higher average latencies on 2024/06/23, possibly suggesting external factors such as load during the data collection period. As per the Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e rows were elminated from the table due to lack of data collected during the period.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eAPI Request (milliseconds) and Routing latency (milliseconds) of physical and conceptual digital twins instances.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eTimestamp\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003enhs-rns-rns01-78h-conceptual-twins-adt\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003enhs-rns-rns01-78h-physical-twins-adt\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAPI Requests Latency (Avg)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRouting Latency (Avg)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAPI Requests Latency (Avg)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRouting Latency (Avg)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e113.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e112.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e319.57\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e31.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e115.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e36.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e348.56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e32.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e121.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e13.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e32.32\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e29.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e109.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e15.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e16.06\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e110.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e64.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e15.40\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e113.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e29.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e228.14\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e36.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e117.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e141.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e201.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e30.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e116.87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e29.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e189.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e239.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e118.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e35.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e148.26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e301.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e113.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e26.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e365.75\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e223.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e106.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e23.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e399.40\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e338.21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e102.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e23.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e37.49\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e26/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e39.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e151.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e208.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e125.79\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e35.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e221.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e184\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e159.55\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e. \u003cb\u003eAPI Request (milliseconds) and Routing latency (milliseconds) of physical and conceptual digital twins instances.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e below shows the number of event triggers from 2024/06/20 to 2024/06/27. The highest number of triggers occurred on 2024/06/22, and the lowest on 2024/06/27. The IoT Hub to SQL DB, IoT Hub to Physical Twins ADT, and Physical Twins ADT to Conceptual Twins ADT recorded similar values for the period, but Conceptual Twins ADT to SQL DB recorded fewer triggers. Additionally, there are inconsistencies in the Conceptual Twins data due to users using the online dashboard to record tasks without using IoT devices. The Conceptual Twins recorded SQL DB triggers only if the task or action was completed. As with Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e and Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e, some rows were eliminated due to a lack of data recorded during the data collection period.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab7\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eFunction trigger count.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eTimestamp\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c5\" namest=\"c2\"\u003e \u003cp\u003eFunction Count (Sum)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eIoT-Hub To\u003c/p\u003e \u003cp\u003eSQL-DB\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eIoT-Hub To\u003c/p\u003e \u003cp\u003ePhysical-Twins-ADT\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePhysical-Twins-ADT To\u003c/p\u003e \u003cp\u003eConceptual-Twins-ADT\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eConceptual-Twins-ADT To\u003c/p\u003e \u003cp\u003eSQL-DB\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e46\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e62\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e24/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e25/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e26/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e. \u003cb\u003eFunction trigger count.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eDuring the initial phase of the implementation, we observed a latency of 10 seconds when querying physical twins. This issue persisted as staff members often recorded both start and end events with brief period of time, despite the fact that tasks generally took more than 10 seconds to be completed for any given scenario. This resulted in duplication of activities and tasks twins in the conceptual twins during each event. To address this latency, we implemented the API calls using Azure SDK to retrieve digital twins as a default rather relying on query. This made querying became less feasible when the digital twins required constant read and write operations.\u003c/p\u003e \u003cp\u003eNotably, the study used dynamically generated instances of digital twins. The digital twins were created or deleted based on the physical overview of the critical care unit. The Table \u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e and \u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e shows the dynamic resource allocation based on the demand. For example, if a newly registered staff member started an activity a new barcode reader, a set of ports, barcode reader, session, staff, activity, and task digital twins would be generated in both physical and conceptual digital twin instances. In such cases, naming digital twins presented unique problems since the naming conventions and Azure Event Grid tend to execute each event nanoseconds apart. So, any standard time-based identification was incompatible and caused unpredictability due to duplication of digital twins. Therefore, globally unique identifiers (GUIDs) were suffixed to digital twins ids to eliminate duplication. Also, GUIDs were used to track each telemetry event from the beginning to the end of the system. A GUID were attached as an identifier to each IoT telemetry event which helped to identify and telemetry track events from the Event Grid.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab8\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDynamic device allocation in IoT Hub\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTimestamp\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTotal devices (Avg)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAttestation attempts (Sum)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRegistration attempts (Sum)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eDevices assigned (Sum)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e26/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab9\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 9\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDynamic twins allocation in Azure Digital Twins.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eTimestamp\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003enhs-rns-rns01-78h-physical-twins-adt\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003enhs-rns-rns01-78h-conceptual-twins-adt\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTwin Count (Sum)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTwin Count (Sum)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e48\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e49\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e50\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e55\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e107\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e67\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e144\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e155\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 12:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e169\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e97\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e193\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e111\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 00:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e233\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e131\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23/06/2024 06:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e235\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e132\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e26/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e242\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e135\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27/06/2024 18:00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e245\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e136\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e. \u003cb\u003eDynamic device allocation in IoT Hub.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e. \u003cb\u003eDynamic twins allocation in Azure Digital Twins.\u003c/b\u003e\u003c/p\u003e \u003cp\u003eMoreover, during the implementation phase of this study the client raised requirements for security, stability, maintainability, and low cost of maintenance. The Microsoft .NET was used as default environment to develop all the software required by the framework as it has more stable releases and documentation. This approach reduced conflicts when projects interact with each other and increased maintainability of the code base. By using Azure SDK for .NET for client and management services helped eliminate many external dependencies which enhanced the security and stability of the code. This approach contributed to the implementation phase the project with less time and improved quality and control in mind.\u003c/p\u003e \u003cp\u003eIn addition, standard or basic features of the Azure platform led to unique challenges. Such as cold start the latency of function apps which would sleep after inactivity and in some cases took at least 90 seconds to start. This caused duplication and errors in the conceptual twins as the digital twins were either not created or did not have updated properties. Instead of implementing queues in the IoT Hub client, the subscription plans were upgraded to premium versions and event grid trigger functions were integrated into a single app project to reduce costs and increase availability. This significantly eliminated data duplication in the conceptual twins.\u003c/p\u003e \u003cp\u003eMoreover, the barcode readers used Bluetooth to communicate with the IoT client computer. Which limited the number of patients that could be covered in the CCU. Barriers and interferences, such as the thick wall dividing the east and west wards and glass dividers restricted the signal strength of each barcode reader to maximum 5 meters. Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows the IoT client\u0026rsquo;s location within the physical layout of the Critical Care Unit (CCU). To record data, manual forms were used as an alternative to cover more patients and to supplement the use of barcode readers. During the production phase many nurse and support staff adopted a hybrid method due to limited access to computers and barcode readers.\u003c/p\u003e \u003cp\u003eNext, Azure uses a global naming schema for identifying its resources. For example, if a resource can establish connectivity with the outside, its name is typically permanent and cannot be changed in the future. Each name also has constraints, such as alphabetical or numerical limits and character length restrictions. Using full names to identify each resource can be complex and may require recreating the entire resource with a different name. To address this, the study employed a four-part naming strategy and used the NHS Digital Data Repository to create a standardized, uniquely readable identification system for naming these resources to overcome the limitations. First, to identify the project, the study used the \u0026ldquo;uod-nhs\u0026rdquo; as University of Derby \u0026ndash; NHS to distinguish other ongoing projects. Secondly, to identify the hospital and unit, formatted as \"rns-rns01-78h,\" which includes the region, hospital ID, and department ID as the prefix. Thirdly, two or three words to identify the project name. Last, initials of the Azure service name, such as \"sqldb\" for SQL Database, \"wa\" for Web App, and \"egt-fa\" for Event Grid Trigger Function Apps, were used. This approach streamlined the naming process, ensuring each resource name was unique among globally deployed resources, and helped scale each resource without causing conflicts.\u003c/p\u003e \u003cp\u003eTo sum up the technology perspective, we noticed that Azure Cloud maintained connectivity with IoT devices throughout the data collection period. The documentation was well-written and easy to implement. Additionally, the IoT Hub executed operations with latency below 1 second. The study's main feature, integrating multiple layers, performed well with latency of less than 500 milliseconds. Azure Entra's application scope helped establish secure, symmetric-key-based applications for each endpoint to manage resources with its built-in HTTP client. The built-in features of the Microsoft SDK helped reduce reliance on external dependencies and facilitated upgrading the source code to more recent stable releases without conflicts. The Azure Resource Manager SDK provided a programmable interface to allocate resources in Azure Cloud, enabling dynamic management of resources. Moreover, the naming strategy reduced clashes between globally deployed resources and streamlined the implementation process.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eFrom a domain perspective, no data was intentionally collected about individual patients or specific workers at first phase. The primary goal was to focus on tracking and quantifying activity while minimizing any potential influence on data collection and performance. This approach ensured that the observed behaviours were as close to natural as possible. The Standard Operating Procedures (SOPs) reviewed during this phase were found to poorly reflect the actual work being performed. A more effective methodology would have involved interviewing various staff members to gain insights into their roles and daily activities. This would have provided a more accurate picture of the work environment and processes. Process mapping for each activity proved valuable in revealing discrepancies between how care was intended to be delivered versus how it was actually delivered. For example, the analysis of nursing documentation revealed that nurses are required to complete 15 separate documents totalling over 80 pages within the first 24 hours of a patient’s admission. Despite the volume, only three did not documents contained redundant information. Analysing and eliminating these redundancies could save approximately 25 minutes per shift, translating to a cumulative reduction of five hours of nursing time per shift, per day. Similarly, more than half of the documentation performed by physiotherapists was found to duplicate nursing reviews. Additionally, the review of pharmacists' roles highlighted that a significant portion of their time was spent retrieving data already gathered by other systems, resulting in redundant tasks with limited value. Another key insight was that during periods of high demand, staff often delayed documentation until after tasks were completed. This suggests that to track activities in real time, data collection must extend beyond documentation to include metrics like changes in patient physiology, position, and interventions provided. As we moved into fault point analysis for Phase 2, it became evident that incident investigations disproportionately attributed errors to individuals, with limited attention given to systemic and process-related factors that contribute to harmful events. The lack of system and process thinking in service design was apparent, and when incidents occurred, the absence of comprehensive data and process maps made it difficult to trace back and identify the root causes. The proposed framework envisioned to incorporate a comparative analysis of activity against an ideal and highlight discrepancies, helping with better understanding of root causes around patient safety events.\u003c/p\u003e \u003cp\u003eDigital Twins (DTs) have their origins in the manufacturing domain, where they were initially applied within Product Lifecycle Management (PLM) systems\u003csup\u003e\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e. To encapsulate the essential features and components of PLM, the \"Mirrored Spaces Model\" was introduced, which consists of real space, virtual space, and a linking mechanism to manage data flow between them. Legacy work (aerospace\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e, energy\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e, maritime\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e) shows capabilities and intent of DTs were well-suited not only to the manufacturing industry\u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e but other domains as well. As their potential became evident, DTs gained attention from other sectors, becoming a strategic technology for key business players\u003csup\u003e\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e. Although DTs are now being explored in diverse domains, including healthcare, achieving optimal benefits relies on how well the domain aligns with the core characteristics of DT models\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u003c/sup\u003e. For example, in the aerospace qualification domain, there is a clear alignment between physical objects (POs) and their virtual DT counterparts, making it straightforward to model DT properties according to the characteristics of the POs. For instance, the \"Reflection\" property\u003csup\u003e\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e can be easily implemented to mirror the behaviour of a robotic system (Cobot) in both physical and digital environments, enabling synchronization of state changes\u003csup\u003e\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u003c/sup\u003e. However, realizing similar capabilities in healthcare is more complex. Healthcare POs are not limited to tangible physical objects (e.g., blood pressure devices); they can also include live observations, workflows, patients, clinicians, or clinical guidelines. Moreover, a single PO may be linked to multiple other POs, each with its own representative DT model. For example, in this study, a barcode device is associated with different roles (nurses, consultants, etc.), each with its own DT model to track activities within the CCU. This creates a many-to-many relationship between healthcare POs and DTs, complicating the design and implementation of DT models in this domain. To address these complexities, a novel layered approach for DT design is proposed. The Physical Digital Twin (PDT) layer represents twins associated with tangible objects and their complementing components—for instance, a barcode scanner and its communication ports. The Conceptual Digital Twin (CDT) layer represents twins of key domain entities, such as roles (nurses, consultants), workflows, observations, and tasks (e.g., CCU forms), which are crucial to fulfilling the business requirements. This multi-layered approach offers two primary advantages: first, it reduces the complexity of domain modelling; second, it allows for a more comprehensive realization of DT capabilities, maximizing their benefits in healthcare applications.\u003c/p\u003e \u003cp\u003eThe current phase of the DT4CCU framework was implemented as an additional task within the existing workflow. This approach limited both the quantity and type of data we could collect due to the demanding environment of the CCU. Our focus in this phase was primarily on capturing the start and end times of tasks, rather than the granular details of the tasks themselves, due to the complexities of recording data while administering lifesaving treatments. It became clear that collecting data for a digital twin framework as an extra task for staff is not feasible, especially as some staff members were initially hesitant to use it. Nevertheless, the framework’s design is flexible enough to integrate various data sources, and in subsequent phases, data from EMRs and other EHRs will be incorporated.\u003c/p\u003e \u003cp\u003eFrom a platform perspective, Azure Cloud reduced the time spent on implementing the DT framework due to its extensive documentation and the trustworthy environment it provides to secure interactions. The key limitation, however, is the lack of in-house capability to replicate Azure services. Open-source frameworks such as Eclipse Ditto and Hono offer alternatives for implementing DT4CCU on-premises\u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e However, implementing an open-source framework in a high-risk industry such as healthcare conflicts with their liability risks. Also, open-source Alternatives such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) were considered due to their performance in Apache benchmarks\u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e, but the NHS infrastructure is based on Microsoft Windows OS. To reduce architectural conflicts and enhance security, study chose Microsoft's Azure Cloud to implement this framework. The Critical Care Unit (CCU) adapts to patient demand and staff availability, causing fluctuations in the need for barcode readers. To reflect these changes, the study integrated the IoT Hub client application with an HTTP API, allowing dynamic management of IoT devices in the cloud based on demand. The endpoint used for managing IoT devices—enabling creation, reading of symmetric keys, and deletion operations in Azure IoT Hub via the Device Provisioning Service—was secured to be accessible only by the IoT Hub client application using Azure Entra scope. Additionally, requiring a symmetric key in the HTTP request headers further enhanced security, enabling real-time adjustments to the digital twins based on demand.\u003c/p\u003e \u003cp\u003eFrom an interdisciplinary perspective, the way we have designed the digital twin can easily be used in other industries where human resources and complex rules are an essential part of the delivery of services. Another group that would benefit from this approach is where predictive judgment is required for complex data with limited information for people to make decisions. These two unique characteristics of our digital twin design mean that it can, on one hand, improve efficiency and be easily deployable in complex environments like government departments, such as taxation, and similarly be useful for entities like small businesses to help with the visualization and validation of their day-to-day operations. Other examples would include the insurance industry, where predictive judgment is an essential part of calculations. This is achievable because we have structured the information around known models of service design and business management, with the intention that experts do not need to face a sharp learning curve to introduce the technology. As we design interfaces as part of phase 2, our next focus will be on designing them in a manner that allows people with limited knowledge of system design and processes to easily build a twin without direct expert input. Our motivation remains healthcare, a field that changes how things are done significantly and regularly, yet we believe that such an approach would potentially allow our model to be used in most industries where even people with limited knowledge of digital twinning can apply the technology to meet their needs.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e "},{"header":"Methods","content":"\u003cp\u003eThe proposed framework employs a four-step process model, systematically divided into five distinct phases. Each phase utilizes the four-step process, as illustrated in Fig. \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003e1) \u003cstrong\u003eDomain Knowledge Acquisition\u003c/strong\u003e: Conceptual Digital Twins (CDTs) are created through a thorough inspection and process mapping of takt time analysis, critical care unit guidelines, and forms used to document the treatment process.\u003c/p\u003e\n\u003cp\u003e2) \u003cstrong\u003eKey Resources Knowledge Acquisition\u003c/strong\u003e: Physical Digital Twins (PDTs) are developed by analysing workflows and business processes (e.g., BPMN, schemas, and protocols) using data from EMR systems, diagnostic devices, and observation forms.\u003c/p\u003e\n\u003cp\u003e3) \u003cstrong\u003eIntegration of PDT and CDT\u003c/strong\u003e: The PDT and CDT models are combined into a unified framework that reflects all relationships and mappings between the components.\u003c/p\u003e\n\u003cp\u003e4) \u003cstrong\u003eDesign Evaluation and Execution\u003c/strong\u003e: The design is validated against artifacts in the target platform (Microsoft Azure in this case) to ensure robust implementation and execution environments.\u003c/p\u003e\n\u003cp\u003eThroughout this process, the overall design aligns with the foundational criteria and requirements specific to the healthcare domain. For instance, domain knowledge is acquired through rigorous inspection of workflows, CCU forms, protocols, guidelines, and consultations with healthcare professionals. The design undergoes comprehensive validation through testing and baseline verification to ensure consistency. Additionally, the design incorporates criteria for compliance with healthcare standards (e.g., security and communication protocols like HL7). Finally, the knowledge generated from the DT models can be shared across other organizations.\u003c/p\u003e\n\u003cp\u003e1) Domain Knowledge Acquisition\u003c/p\u003e\n\u003cp\u003eIdentifying process maps is a key part of creating the Conceptual Digital Twins Layer (CDTL). During the design phase, we scanned observation forms (n\u0026thinsp;=\u0026thinsp;116) to classify them according to the related processes carried out by nurses and doctors. These paper-based observation forms were empty, containing no patient-related data, and were used to identify data points and the structure of the diagnosis and treatment processes. Due to the unstructured nature of tasks performed by doctors, we created process maps (n\u0026thinsp;=\u0026thinsp;1) using forms to record daily entries (n\u0026thinsp;=\u0026thinsp;21). In contrast, the structured nature of tasks performed by nurses led to create process maps (n\u0026thinsp;=\u0026thinsp;6) using forms to document 1) daily entries (n\u0026thinsp;=\u0026thinsp;22) 2) peri-operative tasks (n\u0026thinsp;=\u0026thinsp;1) 3) medical diseases (n\u0026thinsp;=\u0026thinsp;1) 4) procedure lines (n\u0026thinsp;=\u0026thinsp;1) 5) admissions (n\u0026thinsp;=\u0026thinsp;1) 6) death and dying processes (n\u0026thinsp;=\u0026thinsp;1). The study was limited in time and scope, focusing on user roles (n\u0026thinsp;=\u0026thinsp;2), with process maps created for doctors (n\u0026thinsp;=\u0026thinsp;1) and nurses (n\u0026thinsp;=\u0026thinsp;6). Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e10\u003c/span\u003e shows classification of observation forms used in diagnosis and treatment tasks by doctors and nurses based on process groups. As shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e the classification was then mapped into process maps to identify the rules, roles, processes, and standards of each workflow. Breaking down each task into a flowchart helped to communicate domain knowledge about tasks and activities in the Critical Care Unit to technical experts. During this phase, the study identified forms, tasks, actions, patients, staff, and units as Conceptual Digital Twins (CDT).\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003ctable id=\"Tab10\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 10\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eClassification of observation forms used in diagnosis and treatment tasks by doctors and nurses into process groups.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eRole\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eProcess Map\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eTasks\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDoctor\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDaily Entries\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) WZW101 09/17 Clinical Notes 2) NGV903 03/19 Consent Form 1 - Patient Agreement to Investigate or Treatment 3) NGV1220 04/23 Critical Care Unit Prescription and Administration Record 4) NGV1284 10/17 Critical Care Patient and Family Communication Record 5) NGV1550A 09/23 Treatment Escalation Plan (TEP) To be completed for all patients 6) NGV1914 01/18 Critical Care Unit Daily Review 7) NGV2031 11/20 Do not Attempt Cardiopulmonary Resuscitation 8) NGV2035 04/18 Critical Care Microbiology Report 9) NGV2064 07/22 Critical Care Unit Admission 10) NGV2343 06/21 Major Haemorrhage Protocol Blood Administration Record Dial 2222 11) Medical Admission Data\u003c/p\u003e\n \u003cp\u003e12) Critical Care Microbiology Results Record 13) Invasive Procedure Safety Checklist: Tracheostomy 14) Invasive Procedure Safety Checklist: CVC/Dialysis Catheter/PICC Insertion 15) Invasive Procedure Safety Checklist: Arterial Line 16) Procedure Checklist: Pruning 17) Mental Capacity Assessment 18) Patient Demographics 19) Parental Nutrition Prescription 20) Medical Discharge Data\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"6\"\u003e\n \u003cp\u003eNurse\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDaily Entries\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) FNGV1626 13/18 Malnutrition Universal Screening Tool (Must) and Core Care Plan (Adult) 2) WZP198 10/17 Fluid Balance Charts (Adults) 3) WZP538 01/19 Observation Chart for NEWS (National Early Warning Score) 4) NGV785 11/22 Critical Care Unit 5) NGV836 12/21 Adult Prescription and Administration Record 6) NGV1220 04/23 Critical Care Unit Prescription and Administration Record 7) NGV1284 10/17 Critical Care Patient and Family Communication Record 8) NGV1497 12/17 Patient Orientation Checklist - Nursing Staff to Complete 9) NGV1516 10/15 This is my Hospital Passport For people with learning disabilities coming to hospital 10) NGV1580 05/18 Adult Inpatient Admission Information Essential Assessments Activities of Daily Living Initial ADL Assessment 11) NGV1742 03/17 Critical Care Pressure Ulcer Prevention Assessment and Core Care Plan (Adult) 12) NGV1835 06/19 Nurse Handover/Transfer Safety Checklist for Receiving Ward 13) NGV1881 03/16 Duty of Candour Member of Staff carrying out Duty of Candour 14) NGV1914 01/18 Critical Care Unit Daily Review 15) NGV2431 08/21 Summary of Wound Care 16) NGV2441 04/22 Critical Care Nursing Transfer Form 17) NGV2444 03/23 Critical Care Eye Care Plan 18) NGV2485 01/22 Bowel Monitoring Care Plan 19) NGV2690 10/23 Critical Care Transfer Safety Checklist for Receiving Ward 20) Critical Care Water low Risk Assessment Score 21) NGV541 01/14 Trust Falls Assessment and Core Care Plan (Adult) 22) NGV1358 10/17 Trust Initial Pressure Ulcer Assessment (Adult)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePeri-Operative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) WZQ552 03/21 Peri-operative Care Pathway 2) PC711 12/08 Trust core care plan colostomy/ileostomy 3) NGV1380 12/10 Trust Core Neurovascular Limb Assessment (Adult)\u003c/p\u003e\n \u003cp\u003e4) PC1384 01/18 Assessment to be carried out before elective surgery and/or endoscopy to identify patients with or at increased risk of OCJ or vCJD 5) NGV2431 08/21 Summary of Wound Care 6) F-105 Maintenance Check List Faecal Collection System\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMedical Diseases\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) NGV285 03/03 Fit Chart 2) NGV312 02/16 Adult neurological observation chart incorporating pupillary response and limb movements 3) NGV889 11/04 EU Peak Flow Chart \u0026ndash; Inpatient 4) NGV1424 03/23 Adult Insulin Prescription and Diabetes 5) NGV1598 05/18 Diabetes sugar monitoring chart for patients not on insulin 6) Glasgow Modified Alcohol Withdrawal Scale (GMAWS)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eProcedure Lines\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) NGV1176 07/19 Trust Peripheral Venous Cannula (PVC) Care Plan (Adult) 2) NGV1586 03/18 Wound Care Plan 3) NGV1660 03/14 Trust Core Care Plan and Risk Assessment for Patients with Nasogastric Feeding Tube (Adult) 4) NGV1590a 07/17 Trust Core Care Plan Care of the Patient with an Indwelling Urinary Catheter (Adult) 5) NGV090 08/22 Adult Acute Pain Service Patient Controlled Analgesia 6) NGV1239 05/18 Trust Critical Care Arterial Cannula (AC) Care Plan 7) NGV1644 02/16 Trust Core Care Plan: Tracheostomy (Adult) 8) NGV1771 09/20 Adult Transfusion Prescription and Administration Record 9) NGV1798 10/20 Diabetic Ketoacidosis (DKA) Management for Adults 10) NGV1854 05/18 Intravenous Heparin Chart 11) Critical Care Therapies Treatment Record 12) Critical Care Continuous Renal Replacement Therapy Prescription Form \u0026amp; Chart for Citrate 13) MRI Patient Screening Questionnaire and Consent Form\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAdmissions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) NGV1523 07/18 Trust Bedrail Assessment and Core Care Plan (Adult) 2) NGV1545 08/18 Trust Pain Assessment Tool and Core Care Plan for Patients with Learning Disabilities (Adults) and Patients who have Dementia or Cognitive Impairment 3) WZQ552 03/21 Peri-operative Care Pathway 4) NGV1349 08/17 Food Record Chart Nutrition and Diabetic Services 5) NGV2109 07/20 Critical Care Nursing Assessments and Care Plans 6) Critical Care Patient Property Form 7) Parental Nutrition: Initial Review Form 8) Trust Core Patient Activities of Daily Living - Initial Assessment 9) Trust Bedrail Assessment and Core Care Plan (Adult)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDeath and dying\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1) NGV093 01/21 Mortuary Card 2) NGV1274 05/20 Notification of death of a patient - checklist Retain on front of notes 3) NGV1715 06/17 Clinical Notes Achieving Individual Priorities of Care for the Dying Person and their family Doctor Review 4) NGV1717 06/19 Individualised care at the end of life - Care round record sheet (To be used in place of enhanced are round document) 5) NGV1718 03/18 Clinical Notes Individualised Care for the Dying Person and their family (Continued) 6) NGV1720 08/17 Individualised Plan of Care for the Dying Person and their Family Multidisciplinary Communication Sheet 7) NGV2245 04/20 Death Verification Report 8) Tissue Donation Referral Form \u0026ndash; Email 9) H. M. Coroner - Referral Form 10) End of life care checklist\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n\u003c/div\u003e\n\u003cp\u003eTable\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e10\u003c/span\u003e. \u003cstrong\u003eClassification of observation forms used in diagnosis and treatment tasks by doctors and nurses into process groups.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e2) Key Resources Knowledge Acquisition\u003c/p\u003e\n\u003cp\u003eWe observed non-patient medical data, diagnostic devices, and observation forms used in diagnosis and treatment processes to analyse the business and workflow of the critical care unit in order to build the Physical Digital Twins Layer (PDTL). During this phase, alternatives such as web, mobile, and desktop apps were considered to interface physical twins with digital twins, but the study employed a hybrid approach which utilized barcode readers as IoT devices, paper sheets for taking manual entries, and a web-based interface to record the start and end times of tasks by the staff. The main reason for this approach was to provide alternative means for clinicians to interface with the digital twins without changing existing workflows. This phase, the study identified the computer, barcode reader, sessions, and unit as Physical Digital Twins (PDT) within the digital twins framework.\u003c/p\u003e\n\u003cp\u003e3) Integration of PDT and CDT\u003c/p\u003e\n\u003cp\u003eDuring this phase, we identified the session digital twins to store information about the recorded event. The Session CDT was designed to store property values such as Patient ID, Staff ID, Form ID, Start and End Timestamps, and an Is Session Valid Boolean flag. If the Is Session Valid flag is true, then the values in the property fields will be matched with existing twins in the CDTL. For example, if a new staff member initiates an action on a task for an admitted patient, the Session PDT is used to create new Staff CDT, Patient CDT, Task CDT, and Action CDT. The Task CDT and Action CDT are used to record the start and end timestamps. Every time they interact with the patient, a new Action CDT will be created under their particular Task CDT, recording their start and end timestamps. In the above example, if the staff member completes the action, they will set the Is Action Completed Boolean flag to true and update the end timestamp property fields. If the staff member completes a task, the Task CDT will have the Is Task Completed flag set to true, and the end timestamp property fields will be updated. When a staff member creates another action on the same Task CDT, a new Task CDT will be created, and ongoing actions will be displayed under the new Task CDT.\u003c/p\u003e\n\u003cp\u003e4) Design, Evaluation and Execution\u003c/p\u003e\n\u003cp\u003eDesign\u003c/p\u003e\n\u003ch3\u003eDigital Twins Definition Language (DTDL)\u003c/h3\u003e\n\u003cp\u003eThe Digital Twins Definition Language (DTDL) is used to describe the physical twin. Each physical twin is encapsulated in a DTDL model, which is a JSON file that describes the properties and relationships. These DTDL models are then used to create digital twin instances in both PDTL and CDTL. Properties are used to store the states and changes of a particular digital twin by using basic property types or complex property types. The study only used basic property types, as these do not store complex values such as patient treatment details.\u003c/p\u003e\n\u003cp\u003eEach DTDL model can then be used to establish relationships with other models. Due to limitations in the Azure Digital Twins platform, we used DTDL v2 to describe these instances and utilized the Azure SDK to perform create, read, update, and delete operations for digital twin instances and their relationships.\u003c/p\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\n \u003ch2\u003ePhysical Digital Twins Layer (PDTL)\u003c/h2\u003e\n \u003cp\u003eWe designed the Physical Digital Twins Layer (PDTL) and respective cohorts as Physical Digital Twin (PDT) in the framework based on means identified for gathering data. Due to time and scope limitations, only barcode readers were used in the study, referred to as IoT devices. The Unit PDT denoted by CCG Entity Code. We did not use the abbreviations which distinguishes other wards such as the Critical Care Unit (CCU) or Coronary Care Unit (CCU) for staff. Similar examples include Forrest Centre (FC) - Fracture Clinic (FC), Oncology Centre (OC) - Orthopaedics Children (OC), or single names such as Chiropody, Haematology, Pathology, etc. Additionally, the name length is limited to 1 KB and each name had to be unique. For that reason, the unit was named based on NHS guidelines as 78H rather than CCU or Critical Care Unit.\u003c/p\u003e\n \u003cp\u003eBased on scalability, each Unit PDT is subdivided into Desktop PTDs which are host computers used to gather data. Desktop PDTs were identified by Desktop-{name of the host computer}, which were used to determine the data origin location. In this case, study used a unique identifier for the PC or the name of the IoT client application.\u003c/p\u003e\n \u003cp\u003eThe COM PDTs were added to PDTL to indicate which IoT devices are attached to each port. Rather than including this information as a property value inside the IoT device, it was added separately to identify whether the ports are enabled or disabled and to determine which COM ports are occupied by each wireless barcode reader. The IoT Device PDTs were named as CCU{device number}. This IoT Device PDT stored key data about the IoT device. Each IoT device is then attached to one of the COM ports, as illustrated in Fig. \u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e\n \u003cp\u003eSession PDTs are temporary 30-second virtual sessions used to hold information from barcode readers. During the testing phase, we initially added timestamps with millisecond accuracy as S-{timestamp in milliseconds}. However, this approach was not sustainable in the real world, where events might occur in microseconds or nanoseconds apart. To create unique names for each digital twin, we decided to suffix a GUID as S-{GUID}. This solution addressed the uniqueness problem and avoided duplication issues even the data is ingested in nanoseconds apart. The main limitation of the barcode readers is their inability to process data within the device itself. Each telemetry event from the IoT Hub Client app contained a JSON object with the following structure.\u003c/p\u003e\n \u003cp\u003eThe IoT Hub client app sends the event to the ADT Ingestion in IoT Hub Event Grid Trigger Function App (uod-nhs-rns-rns01-78h-iot-hub-egt-fa/adt-ingestion) to create new sessions and update or replace values for existing valid sessions. The Session PDTs are used to store identifiers for patients, forms, or staff. These Session PDTs help to virtually store and queue relevant information and will be set expired if the properties within them are incomplete or expired. Each Session PDT stored and validated properties such as patient identifier, staff identifier, form identifier, start time, and end time. Once the Session PDT is valid, the property data is mapped to their conceptual twins, the Session PDT set expired, and a snapshot of this instance is stored in the SQL database for validation.\u003c/p\u003e\n \u003cp\u003eConceptual Digital Twins Layer (CDTL)\u003c/p\u003e\n \u003cp\u003eThe Conceptual Digital Twins Layer (CDTL) defines Conceptual Digital Twin (CDT) which is micro-ergonomic data such as rules, roles, processes, and standards twins of the Critical Care Unit (CCU). The data originates from the PDTL, and each snapshot is stored upon completion in a SQL database. The CDTL is interfaced with stakeholders, enabling interaction and generating reports through a web-based graphical user interface. As shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e, the CDTL includes CDTs such as patient, form, task, activity, staff, and unit.\u003c/p\u003e\n \u003cp\u003eNext, demand is created by patients when they are admitted to the unit for diagnosis and treatment. The staff, on the other hand, are equipped with process maps to follow for each patient based on specific criteria. The staff use different types of observation forms to record these diagnosis and treatment procedures for the patient. Subsequently, we were able to generate the framework for the CDTL by creating CDTs for these conceptual elements and mapping them based on the level of interaction using relationships.\u003c/p\u003e\n \u003cp\u003eIn this study, we did not store any patient-specific information or values from personal records. To denote the Patient CDT in the framework an increment value was suffixed to the Patient PDT ID as P-{increment number}, ensuring that each twin ID is unique in the CDTL. This patient ID value is derived from the Session PDT\u0026apos;s Patient ID property.\u003c/p\u003e\n \u003cp\u003eThen, the Form CDT was added to the CDTL to understand the frequency of each observation form type. The Form CDT helps define the type of treatment or diagnosis the Patient CDT is undergoing and assess the bed acuity level. The Form CDT is named with incremental values, such as F-{increment value}, which is an integer. Instead of using the full name of a form, such as \u0026quot;NGV1717 06/19 Individualised Care at the End of Life - Care Round Record Sheet (To be Used in Place of Enhanced Care Round Document)\u0026quot; we shortened it to the form ID F-50. This approach helped reduce errors and cleaned up the knowledge graph representation of the conceptual digital twins. These forms do not contain any patient-related data and are purely used to identify which form is used by the staff.\u003c/p\u003e\n \u003cp\u003eThe Task CDT is an instance of the Form CDT. In the real-world setting, each observation form is used by several staff members over a particular period. For example, the NGV1914 01/18 Critical Care Unit Daily Review observation form is used by clinicians and nurses to record observations such as heart rate or blood pressure and treatments such as medications prescribed for a patient. This form is allocated every 24 hours and is replaced with a new form at the end of the day. In the CDTL, this is considered a Task CDT. If a patient stays for 3 days, it means there are 3 Task CDTs. Each Task CDT is then attached to a Patient CDT and Form CDT recording the start and end times. This setup helps calculate bed acuity levels, costs per patient, the number of times a form has been used, and the average task completion time. The CDTL only allows one Task CDT for one Form CDT at any given instance, which helps identify work duplication and track ongoing tasks. The Task CDT was mapped using the Session PDT\u0026rsquo;s Patient ID, Form ID, and start/end timestamp properties. Each Task CDT included an \u0026quot;Is Task Completed\u0026quot; property which was used by staff to check if the task is completed or not. This resembled the process of changing observation forms in the physical setting. If there are no ongoing tasks, a new Task CDT will be created in CDTL.\u003c/p\u003e\n \u003cp\u003eFurther, the Action CDT is used to record individual sessions within a Task CDT. For example, the NGV1914 01/18 Critical Care Unit Daily Review form involves multiple interactions with doctors and nurses over its 24-hour period. These individual interactions are mapped to specific Action CDTs. Each Action CDT includes properties such as Is Action Completed, Start Timestamp, End Timestamp, Staff ID, and Task ID. When a staff member begins a treatment procedure, they first record the timestamp at the start of the procedure. They then record the second timestamp at the end of the procedure, which notifies the CDTL that the Action CDT has been completed. The CDTL enforces a rule that only one ongoing action is allowed for a specific task at a time by a staff member. Initially, a new Action CDT is created with both the start and end timestamps set to the same value. Once the action is completed, the end timestamp is updated, and the Is Action Completed property is set to true. This approach helps map individual staff interactions with a given task, calculate the time a staff member spends on an action, assess whether a particular staff member is busy, track the timeline of interactions with a patient, and evaluate the costs and efficiency of the treatment process for each patient at a more granular level. The Action CDT does not contain any patient-related data and is purely used to record timestamps.\u003c/p\u003e\n \u003cp\u003eNext, the Staff CDT was used to identify staff members in the CDTL. The Staff CDT does not hold any personal data such as names, ages, or other personal details. Due to scope and time limitations, the study did not store user roles either. Each Staff CDT was named using the format S-{increment value}. The Staff CDT will be created if it does not already exist, and it will then be mapped to the relevant Action CDT based on the Task Id property of the Session PDT.\u003c/p\u003e\n \u003cp\u003eFinally, the Unit CDT was used to map each staff member to their workstation. Currently, the CDTL mapping is used to map staff who work in the Critical Care Unit, specifically unit 78H. However, with scalability in mind future staff from cross-departmental interactions\u0026mdash;such as scanning X-rays or blood checking\u0026mdash;will be mapped based on available data to build a real-time, sophisticated knowledge graph representation of the hospital.\u003c/p\u003e\n \u003cp\u003eExecution\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\n \u003ch2\u003eSoftware Infrastructure\u003c/h2\u003e\n \u003cp\u003eAs shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e, the IoT hub client application provided the interface to manage IoT devices. It established connectivity to the Azure cloud by dynamically generating symmetric keys for each IoT device using an HTTP endpoint. This endpoint was protected by Microsoft Defender for Cloud to identify malicious activities and Microsoft Entra to secure accessibility to endpoints and scopes. The app then retrieved symmetric keys to establish connectivity to the IoT hub Device Provisioning Service (DPS) dynamically based on the availability of devices.\u003c/p\u003e\n \u003cp\u003eThe cloud based digital twins interfaced with the humans using IoT devices and through a web interface. The dynamic nature of allocating cloud resources required flexibility, we used Azure Service Managers to allocate and generate security keys to establish connectivity between the aforementioned services in real-time. By using Function Apps and Event Grids, we captured the event data of IoT Hub and Digital Twins in SQL databases. The web interface provided users with accessibility to interact with these Digital Twins. A set of temporary emails were created using Entra to grant users access to the system.\u003c/p\u003e\n \u003cp\u003eWhen staff scanned values using a barcode reader, the IoT Hub client created a telemetry event containing a JSON payload with information about the PC, IoT device, value, and timestamp. Each telemetry event was then filtered by the IoT hub Event Grid to trigger functions that to store this event data or ingested it into the PDTL based on their characteristics. Then a series of function apps were designed to capture these digital twins update events, on PDTL Event Grid triggers to modify the CDTL accordingly.\u003c/p\u003e\n \u003cp\u003eThe web-based dashboard provided an authenticated user interface for interacting with the Conceptual Twins, allowing users to generate reports such as identifying bed acuity, ongoing tasks and activities, costs by each form, costs by each patient, time taken by each form and staff member, and time spent on each patient. The study was limited in scope and did not build services such as notifying staff of ongoing activities or missing activities based on process maps. However, these potential expansions such as Time Triggers were identified and mentioned in the architecture for the future development.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\n \u003ch2\u003eHardware Infrastructure\u003c/h2\u003e\n \u003cp\u003eDue to computer privacy and security reasons, study did not use any computers connected to the existing NHS network or its private infrastructure. Instead, they used a custom-built PC to deploy the IoT hub client application and connect the IoT devices. This approach provided a greater control over their infrastructure and saved time by avoiding the need to obtain approval from the NHS to run a custom program on one of their.\u003c/p\u003e\n \u003cp\u003eIn the study, we used barcode readers (n\u0026thinsp;=\u0026thinsp;3), specifically Tera 51000 Laser 1D (n\u0026thinsp;=\u0026thinsp;2) and Tera D5100 2D (n\u0026thinsp;=\u0026thinsp;1) wireless barcode scanners. Initially, the plan was to provide a scanner for each patient, but the constraints limited the number due to the coverage limitations of the barcode readers. The main wall dividing the east ward and west ward posed a significant barrier to establish connectivity between patients in farther sections with the IoT hub client application. Additionally, the glass walls separating each bed caused signal disruptions between the IoT client application and the IoT devices.\u003c/p\u003e\n \u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e shows the data points collected during the production phase, which helped create the coverage map displayed above. The map is not according to any scale but used in production to identify availability. Due to these challenges, the use of IoT devices was restricted to beds 6, 7, 8, and E, with bed D being vacant during the data collection period. Consequently, the study had to place a hybrid method that combined both offline and online approaches to collect data, utilizing paper forms and computers.\u003c/p\u003e\n \u003cp\u003eEvaluation\u003c/p\u003e\n \u003cp\u003eThe consent forms were collected from the participants doctors (n\u0026thinsp;=\u0026thinsp;15) and nurses (n\u0026thinsp;=\u0026thinsp;5) at the Critical Care Unit of Northampton General Hospital NHS Trust. These consent forms were generic, not specific to reference what type of information gathered or type of task they performed during the study. Each patient and staff were identified by using custom numbers during the data collection, which was only used by the staff to track the tasks performed for each patient. Any staff and patient specific data were not collected during the study.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\n \u003ch2\u003eOffline\u003c/h2\u003e\n \u003cp\u003eThe offline method was deployed to overcome network issues caused by barriers between patients and the IoT hub client application. This method, staff member could use either IoT devices or simply write on the paper the start and end times. Later on, the data points written on the form were added to the digital twins framework using the online method.\u003c/p\u003e\n\u003c/div\u003e\n\u003ch3\u003eOnline\u003c/h3\u003e\n\u003cp\u003eFirst, temporary emails were provided to each staff member to access the system through the web interface. Each barcode was assigned to a patient to allow staff to gather start and end times efficiently. This system helped track patients when they were moved to other beds based on the severity of their condition. The online method was primarily limited to those who already had access to computers. The online interface featured three user roles: managers, administrators, and staff. The Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e given below shows the web-based dashboard designed for staff.\u003c/p\u003e\n\u003cp\u003eMoreover, based on the data collected in the digital twins, unit managers could generate reports such as average time and costs related to each patient, bed acuity levels at a given time, and the costs generated by forms. Administrators could manage staff member access, create new users, oversee overall resource usage, allocate IoT devices to patients, and manage resources. The staff interface allows users to create, read, and update digital twins, allocate resources, monitor bed acuity levels, track ongoing tasks and actions for respective staff members, mark tasks or actions as complete, and create new actions based on forms.\u003c/p\u003e\n\u003cp\u003eDataset\u003c/p\u003e\n\u003cp\u003eThe dataset was extracted using the Digital Twins Query Language from Digital Twins Instances. Each event did not contain any data related to patients or staff, but rather workflows at the CCU. This data included the start and end timestamps of actions, observation form types, and the digital twins\u0026apos; names for staff and patients. We cleaned the data in the digital twins instances into generalized records, showing the number of minutes spent on each task, categorized by process groups. The dataset is not publicly accessible and is attached as a supplementary file for review purposes.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eData Availability\u003c/p\u003e\n\u003cp\u003eCurrent datasets generated during the study are attached with supplementary files and review only. Once get accepted we can me it available for the public access.\u003c/p\u003e\n\u003cp\u003eCode Availability\u003c/p\u003e\n\u003cp\u003eThe underlying repositories used in this study are not publicly available for proprietary reasons. We will make some parts of the framework\u0026apos;s source code available to the public in the next phases.\u003c/p\u003e\n\u003cp\u003eAuthor Contributions\u003c/p\u003e\n\u003cp\u003eGK implemented the digital twins framework on Azure Cloud and co-authored the discussion, methods, and data and code availability sections. MH drafted the overall manuscript and contributed to the design of the digital twin for CCU. MZ developed process maps, addressed domain-specific aspects of the framework, and co-authored the abstract, introduction, and discussion sections. WAK assisted in reviewing and refining the manuscript. GK, MH, and MZ contributed equally and should be recognized as co-lead authors.\u003c/p\u003e\n\u003cp\u003eAcknowledgments\u003c/p\u003e\n\u003cp\u003eThis project was funded by TechTach Limited and the University of Derby under a joint collaboration agreement (internal project ID: PSL2324-0100). The authors also express their gratitude to the staff members of CCU at Northampton General Hospital, who voluntarily provided domain knowledge and participated in the Digital Twin usage trials.\u003c/p\u003e\n\u003cp\u003eCompeting Interests\u003c/p\u003e\n\u003cp\u003eThe authors declare that no competing of financial interests.\u003c/p\u003e\n\u003cdiv id=\"_com_3\" language=\"JavaScript\"\u003e\u003cbr\u003e\u003c/div\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eWright, L. \u0026amp; Davidson, S. How to tell the difference between a model and a digital twin. \u003cem\u003eAdv Model Simul Eng Sci\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, (2020).\u003c/li\u003e\n\u003cli\u003eSurian, N. U. \u003cem\u003eet al.\u003c/em\u003e A digital twin model incorporating generalized metabolic fluxes to identify and predict chronic kidney disease in type 2 diabetes mellitus. \u003cem\u003eNPJ Digit Med\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, 140 (2024).\u003c/li\u003e\n\u003cli\u003eChu, Y., Li, S., Tang, J. \u0026amp; Wu, H. The potential of the Medical Digital Twin in diabetes management: a review. \u003cem\u003eFront Med (Lausanne)\u003c/em\u003e \u003cstrong\u003e10\u003c/strong\u003e, (2023).\u003c/li\u003e\n\u003cli\u003eWalsh, J. R., Roumpanis, S., Bertolini, D. \u0026amp; Delmar, P. Evaluating Digital Twins for Alzheimer\u0026rsquo;s Disease using Data from a Completed Phase 2 Clinical Trial. \u003cem\u003eAlzheimer\u0026rsquo;s \u0026amp; Dementia\u003c/em\u003e \u003cstrong\u003e18\u003c/strong\u003e, (2022).\u003c/li\u003e\n\u003cli\u003eCorral-Acero, J. \u003cem\u003eet al.\u003c/em\u003e The \u0026lsquo;Digital Twin\u0026rsquo; to enable the vision of precision cardiology. \u003cem\u003eEur Heart J\u003c/em\u003e \u003cstrong\u003e41\u003c/strong\u003e, 4556\u0026ndash;4564 (2020).\u003c/li\u003e\n\u003cli\u003eLin, T.-Y. \u003cem\u003eet al.\u003c/em\u003e Assessing overdiagnosis of fecal immunological test screening for colorectal cancer with a digital twin approach. \u003cem\u003eNPJ Digit Med\u003c/em\u003e \u003cstrong\u003e6\u003c/strong\u003e, 24 (2023).\u003c/li\u003e\n\u003cli\u003eScott, A. K. \u0026amp; Oyen, M. L. Virtual pregnancies: predicting and preventing pregnancy complications with digital twins. \u003cem\u003eLancet Digit Health\u003c/em\u003e \u003cstrong\u003e6\u003c/strong\u003e, e436\u0026ndash;e437 (2024).\u003c/li\u003e\n\u003cli\u003eJin, Z. \u003cem\u003eet al.\u003c/em\u003e Anti- and pro-fibrillatory effects of pulmonary vein isolation gaps in human atrial fibrillation digital twins. \u003cem\u003eNPJ Digit Med\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, 81 (2024).\u003c/li\u003e\n\u003cli\u003eLaubenbacher, R., Sluka, J. P. \u0026amp; Glazier, J. A. Using digital twins in viral infection. \u003cem\u003eScience\u003c/em\u003e vol. 371 Preprint at https://doi.org/10.1126/science.abf3370 (2021).\u003c/li\u003e\n\u003cli\u003ePod\u0026eacute;us, H. \u003cem\u003eet al.\u003c/em\u003e A physiologically-based digital twin for alcohol consumption\u0026mdash;predicting real-life drinking responses and long-term plasma PEth. \u003cem\u003eNPJ Digit Med\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, 112 (2024).\u003c/li\u003e\n\u003cli\u003eVoigt, I. \u003cem\u003eet al.\u003c/em\u003e Digital Twins for Multiple Sclerosis. \u003cem\u003eFront Immunol\u003c/em\u003e \u003cstrong\u003e12\u003c/strong\u003e, (2021).\u003c/li\u003e\n\u003cli\u003eHansen, J., Jain, A. R., Nenov, P., Robinson, P. N. \u0026amp; Iyengar, R. From transcriptomics to digital twins of organ function. \u003cem\u003eFront Cell Dev Biol\u003c/em\u003e \u003cstrong\u003e12\u003c/strong\u003e, (2024).\u003c/li\u003e\n\u003cli\u003eLi, X. \u003cem\u003eet al.\u003c/em\u003e A dynamic single cell-based framework for digital twins to prioritize disease genes and drug targets. \u003cem\u003eGenome Med\u003c/em\u003e \u003cstrong\u003e14\u003c/strong\u003e, 48 (2022).\u003c/li\u003e\n\u003cli\u003eGazerani, P. Intelligent Digital Twins for Personalized Migraine Care. \u003cem\u003eJ Pers Med\u003c/em\u003e \u003cstrong\u003e13\u003c/strong\u003e, 1255 (2023).\u003c/li\u003e\n\u003cli\u003eCorral-Acero, J. \u003cem\u003eet al.\u003c/em\u003e The \u0026lsquo;Digital Twin\u0026rsquo; to enable the vision of precision cardiology. \u003cem\u003eEur Heart J\u003c/em\u003e \u003cstrong\u003e41\u003c/strong\u003e, 4556\u0026ndash;4564 (2020).\u003c/li\u003e\n\u003cli\u003eKatsoulakis, E. \u003cem\u003eet al.\u003c/em\u003e Digital twins for health: a scoping review. \u003cem\u003eNPJ Digit Med\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, 77 (2024).\u003c/li\u003e\n\u003cli\u003eTresfon, J., Brunsveld-Reinders, A. H., Van Valkenburg, D., Langeveld, K. \u0026amp; Hamming, J. Aligning work-as-imagined and work-as-done using FRAM on a hospital ward: a roadmap. \u003cem\u003eBMJ Open Qual\u003c/em\u003e \u003cstrong\u003e11\u003c/strong\u003e, (2022).\u003c/li\u003e\n\u003cli\u003eAlyahya, M. S. \u003cem\u003eet al.\u003c/em\u003e The association between cognitive medical errors and their contributing organizational and individual factors. \u003cem\u003eRisk Manag Healthc Policy\u003c/em\u003e \u003cstrong\u003e14\u003c/strong\u003e, (2021).\u003c/li\u003e\n\u003cli\u003eIllingworth J \u003cem\u003eet al.\u003c/em\u003e \u003cem\u003eThe National State of Patient Safety: What We Know about Avoidable Harm in England\u003c/em\u003e. (2022).\u003c/li\u003e\n\u003cli\u003eAhsani-Estahbanati, E., Doshmangir, L., Najafi, B., Akbari Sari, A. \u0026amp; Sergeevich Gordeev, V. Incidence rate and financial burden of medical errors and policy interventions to address them: a multi-method study protocol. \u003cem\u003eHealth Serv Outcomes Res Methodol\u003c/em\u003e \u003cstrong\u003e22\u003c/strong\u003e, 244\u0026ndash;252 (2022).\u003c/li\u003e\n\u003cli\u003eOrganization, W. H. \u003cem\u003eGlobal Patient Safety Report 2024\u003c/em\u003e. (World Health Organization, Geneva, 2024).\u003c/li\u003e\n\u003cli\u003eThe Faculty of Intensive Care Medicine (FICM) \u0026amp; Intensive Care Society (ICS). Guidelines for the Provision of Intensive Care Services (GPICS). \u003cem\u003eGPICS v2.1\u003c/em\u003e https://www.ficm.ac.uk/standards/guidelines-for-the-provision-of-intensive-care-services (2022).\u003c/li\u003e\n\u003cli\u003eNHS England. A just culture guide. https://www.england.nhs.uk/patient-safety/patient-safety-culture/a-just-culture-guide/.\u003c/li\u003e\n\u003cli\u003eCarayon, P., Wooldridge, A., Hoonakker, P., Hundt, A. S. \u0026amp; Kelly, M. M. SEIPS 3.0: Human-centered design of the patient journey for patient safety. \u003cem\u003eAppl Ergon\u003c/em\u003e \u003cstrong\u003e84\u003c/strong\u003e, (2020).\u003c/li\u003e\n\u003cli\u003eJalali, M., Dehghan, H., Habibi, E. \u0026amp; Khakzad, N. Application of \u0026ldquo;Human Factor Analysis and Classification System\u0026rdquo; (HFACS) Model to the Prevention of Medical Errors and Adverse Events: A Systematic Review. \u003cem\u003eInternational Journal of Preventive Medicine\u003c/em\u003e vol. 14 Preprint at https://doi.org/10.4103/ijpvm.ijpvm_123_22 (2023).\u003c/li\u003e\n\u003cli\u003eKaushik, P., Rao, A. M., Singh, D. P., Vashisht, S. \u0026amp; Gupta, S. Cloud Computing and Comparison based on Service and Performance between Amazon AWS, Microsoft Azure, and Google Cloud. in \u003cem\u003eProceedings of International Conference on Technological Advancements and Innovations, ICTAI 2021\u003c/em\u003e (2021). doi:10.1109/ICTAI53825.2021.9673425.\u003c/li\u003e\n\u003cli\u003eKherbache, M., Maimour, M. \u0026amp; Rondeau, E. Digital Twin Network for the IIoT using Eclipse Ditto and Hono. in \u003cem\u003eIFAC-PapersOnLine\u003c/em\u003e vol. 55 (2022).\u003c/li\u003e\n\u003cli\u003eGrieves, M. \u003cem\u003eOrigins of the Digital Twin Concept\u003c/em\u003e. (2016). doi:10.13140/RG.2.2.26367.61609.\u003c/li\u003e\n\u003cli\u003eBisanti, G. M., Mainetti, L., Montanaro, T., Patrono, L. \u0026amp; Sergi, I. Digital twins for aircraft maintenance and operation: A systematic literature review and an IoT-enabled modular architecture. \u003cem\u003eInternet of Things\u003c/em\u003e \u003cstrong\u003e24\u003c/strong\u003e, 100991 (2023).\u003c/li\u003e\n\u003cli\u003eJiang, Y. \u003cem\u003eet al.\u003c/em\u003e Multi-domain ubiquitous digital twin model for information management of complex infrastructure systems. \u003cem\u003eAdvanced Engineering Informatics\u003c/em\u003e \u003cstrong\u003e56\u003c/strong\u003e, 101951 (2023).\u003c/li\u003e\n\u003cli\u003eMadusanka, N. S., Fan, Y., Yang, S. \u0026amp; Xiang, X. Digital Twin in the Maritime Domain: A Review and Emerging Trends. \u003cem\u003eJ Mar Sci Eng\u003c/em\u003e \u003cstrong\u003e11\u003c/strong\u003e, 1021 (2023).\u003c/li\u003e\n\u003cli\u003eTao, F., Zhang, H. \u0026amp; Zhang, C. Advancements and challenges of digital twins in industry. \u003cem\u003eNat Comput Sci\u003c/em\u003e \u003cstrong\u003e4\u003c/strong\u003e, 169\u0026ndash;177 (2024).\u003c/li\u003e\n\u003cli\u003eSingh, M. \u003cem\u003eet al.\u003c/em\u003e Digital Twin: Origin to Future. \u003cem\u003eApplied System Innovation\u003c/em\u003e \u003cstrong\u003e4\u003c/strong\u003e, 36 (2021).\u003c/li\u003e\n\u003cli\u003eGeoffrey Chase, J. \u003cem\u003eet al.\u003c/em\u003e Digital Twins in Critical Care: What, When, How, Where, Why? \u003cem\u003eIFAC-PapersOnLine\u003c/em\u003e \u003cstrong\u003e54\u003c/strong\u003e, 310\u0026ndash;315 (2021).\u003c/li\u003e\n\u003cli\u003eMinerva, R. \u0026amp; Crespi, N. Digital Twins: Properties, Software Frameworks, and Application Scenarios. \u003cem\u003eIT Prof\u003c/em\u003e \u003cstrong\u003e23\u003c/strong\u003e, 51\u0026ndash;55 (2021).\u003c/li\u003e\n\u003cli\u003eAwill, R., Khan, W. A., Hussain, M., Zada, S. \u0026amp; Anderson, B. Aerospace Qualification Services Knowledge Graph: A Leap towards Enhanced Data Management. in \u003cem\u003eCEUR Workshop Proceedings\u003c/em\u003e vol. 3632 (2023).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5010353/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5010353/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDigital twins, long utilized in industries for enhancing efficiency, maintenance, real-time monitoring, and sustainability, are now gaining traction in healthcare, particularly with a disease-focused approach. This paper presents our journey towards the realization of a Digital Twin framework specifically designed for Critical Care, emphasizing patient safety, operational efficiency, and sustainability. Our Digital Twin architecture is uniquely structured with a dual-layer approach: a physical twin monitors real-time activities, while a conceptual twin represents ideal workflows. In Phase 1 of our research work, we aim to establish a methodology for live activity tracking. Our findings indicate that by reviewing documentation alone, we could successfully track 72% of tasks performed by nursing staff and physicians in real time. These results underscore the potential of Digital Twins to transform critical care delivery by bridging the gap between actual and ideal clinical practices.\u003c/p\u003e","manuscriptTitle":"DT4CCU – A Digital Twins framework for Critical Care Unit","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-18 10:14:09","doi":"10.21203/rs.3.rs-5010353/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-31T01:00:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-18T18:47:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-09T02:56:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"124139528564867024763467982989588216890","date":"2024-12-05T14:31:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"70347099574320481119773797919106898734","date":"2024-11-30T14:06:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"4867992834723937736623442236828577594","date":"2024-11-29T18:06:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-21T18:47:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"56263093209714256943681669587234008196","date":"2024-10-16T05:19:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-09-16T02:39:41+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-03T00:54:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-09-02T06:08:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2024-08-31T19:12:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a911bdbc-7f22-4919-bf89-2b6ca507f77c","owner":[],"postedDate":"October 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-23T16:00:20+00:00","versionOfRecord":{"articleIdentity":"rs-5010353","link":"https://doi.org/10.1038/s41746-025-01738-4","journal":{"identity":"npj-digital-medicine","isVorOnly":false,"title":"npj Digital Medicine"},"publishedOn":"2025-06-19 15:57:19","publishedOnDateReadable":"June 19th, 2025"},"versionCreatedAt":"2024-10-18 10:14:09","video":"","vorDoi":"10.1038/s41746-025-01738-4","vorDoiUrl":"https://doi.org/10.1038/s41746-025-01738-4","workflowStages":[]},"version":"v1","identity":"rs-5010353","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5010353","identity":"rs-5010353","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}